diff --git a/data/com.jeffser.Alpaca.metainfo.xml.in b/data/com.jeffser.Alpaca.metainfo.xml.in
index cc13e58..2f18101 100644
--- a/data/com.jeffser.Alpaca.metainfo.xml.in
+++ b/data/com.jeffser.Alpaca.metainfo.xml.in
@@ -77,6 +77,7 @@
The new icon was made by Tobias Bernard over the Gnome Gitlab, thanks for the great icon!
Features and fixes
+ - Updated Ollama instance to 0.2.8
- Better model selector
- Model manager redesign
- Better tag selector when pulling a model
@@ -103,6 +104,18 @@
- Auto-hiding sidebar button
- Various UI tweaks
+ New Models
+
+ - Gemma2
+ - GLM4
+ - Codegeex4
+ - InternLM2
+ - Llama3-groq-tool-use
+ - Mathstral
+ - Mistral-nemo
+ - Firefunction-v2
+ - Nuextract
+
Translations
These are all the available translations on 1.0.0, thanks to all the contributors!
diff --git a/src/available_models.json b/src/available_models.json
index bcf835c..e8411ab 100644
--- a/src/available_models.json
+++ b/src/available_models.json
@@ -75,6 +75,66 @@
"27b-instruct-q8_0",
"29GB"
],
+ [
+ "27b-text-fp16",
+ "54GB"
+ ],
+ [
+ "27b-text-q2_K",
+ "10GB"
+ ],
+ [
+ "27b-text-q3_K_L",
+ "15GB"
+ ],
+ [
+ "27b-text-q3_K_M",
+ "13GB"
+ ],
+ [
+ "27b-text-q3_K_S",
+ "12GB"
+ ],
+ [
+ "27b-text-q4_0",
+ "16GB"
+ ],
+ [
+ "27b-text-q4_1",
+ "17GB"
+ ],
+ [
+ "27b-text-q4_K_M",
+ "17GB"
+ ],
+ [
+ "27b-text-q4_K_S",
+ "16GB"
+ ],
+ [
+ "27b-text-q5_0",
+ "19GB"
+ ],
+ [
+ "27b-text-q5_1",
+ "21GB"
+ ],
+ [
+ "27b-text-q5_K_M",
+ "19GB"
+ ],
+ [
+ "27b-text-q5_K_S",
+ "19GB"
+ ],
+ [
+ "27b-text-q6_K",
+ "22GB"
+ ],
+ [
+ "27b-text-q8_0",
+ "29GB"
+ ],
[
"9b-instruct-fp16",
"18GB"
@@ -134,6 +194,66 @@
[
"9b-instruct-q8_0",
"9.8GB"
+ ],
+ [
+ "9b-text-fp16",
+ "18GB"
+ ],
+ [
+ "9b-text-q2_K",
+ "3.8GB"
+ ],
+ [
+ "9b-text-q3_K_L",
+ "5.1GB"
+ ],
+ [
+ "9b-text-q3_K_M",
+ "4.8GB"
+ ],
+ [
+ "9b-text-q3_K_S",
+ "4.3GB"
+ ],
+ [
+ "9b-text-q4_0",
+ "5.4GB"
+ ],
+ [
+ "9b-text-q4_1",
+ "6.0GB"
+ ],
+ [
+ "9b-text-q4_K_M",
+ "5.8GB"
+ ],
+ [
+ "9b-text-q4_K_S",
+ "5.5GB"
+ ],
+ [
+ "9b-text-q5_0",
+ "6.5GB"
+ ],
+ [
+ "9b-text-q5_1",
+ "7.0GB"
+ ],
+ [
+ "9b-text-q5_K_M",
+ "6.6GB"
+ ],
+ [
+ "9b-text-q5_K_S",
+ "6.5GB"
+ ],
+ [
+ "9b-text-q6_K",
+ "7.6GB"
+ ],
+ [
+ "9b-text-q8_0",
+ "9.8GB"
]
],
"image": false,
@@ -1029,7 +1149,7 @@
"tags": [
[
"latest",
- "2.4GB"
+ "2.2GB"
],
[
"14b",
@@ -1037,11 +1157,11 @@
],
[
"3.8b",
- "2.4GB"
+ "2.2GB"
],
[
"instruct",
- "2.4GB"
+ "2.2GB"
],
[
"medium",
@@ -1049,18 +1169,18 @@
],
[
"mini",
- "2.4GB"
+ "2.2GB"
],
[
"14b-instruct",
"7.9GB"
],
[
- "14b-medium-128k-instruct-f16",
+ "14b-medium-4k-instruct-f16",
"28GB"
],
[
- "14b-medium-4k-instruct-f16",
+ "14b-medium-128k-instruct-f16",
"28GB"
],
[
@@ -1173,14 +1293,18 @@
],
[
"3.8b-instruct",
- "2.4GB"
+ "2.2GB"
+ ],
+ [
+ "3.8b-mini-4k-instruct-f16",
+ "7.6GB"
],
[
"3.8b-mini-128k-instruct-f16",
"7.6GB"
],
[
- "3.8b-mini-4k-instruct-f16",
+ "3.8b-mini-128k-instruct-fp16",
"7.6GB"
],
[
@@ -1239,6 +1363,10 @@
"3.8b-mini-128k-instruct-q8_0",
"4.1GB"
],
+ [
+ "3.8b-mini-4k-instruct-fp16",
+ "7.6GB"
+ ],
[
"3.8b-mini-4k-instruct-q2_K",
"1.4GB"
@@ -1306,6 +1434,10 @@
[
"medium-128k",
"7.9GB"
+ ],
+ [
+ "mini-4k",
+ "2.4GB"
]
],
"image": false,
@@ -1327,14 +1459,14 @@
"8b",
"4.8GB"
],
- [
- "35b-23",
- "20GB"
- ],
[
"35b-23-f16",
"70GB"
],
+ [
+ "35b-23",
+ "20GB"
+ ],
[
"35b-23-q2_K",
"14GB"
@@ -1391,14 +1523,14 @@
"35b-23-q8_0",
"37GB"
],
- [
- "8b-23-f16",
- "16GB"
- ],
[
"8b-23",
"4.8GB"
],
+ [
+ "8b-23-f16",
+ "16GB"
+ ],
[
"8b-23-q2_K",
"3.4GB"
@@ -1495,101 +1627,17 @@
"7b-instruct",
"4.1GB"
],
- [
- "7b-instruct-fp16",
- "14GB"
- ],
- [
- "7b-instruct-q2_K",
- "3.1GB"
- ],
- [
- "7b-instruct-q3_K_L",
- "3.8GB"
- ],
- [
- "7b-instruct-q3_K_M",
- "3.5GB"
- ],
- [
- "7b-instruct-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-instruct-q4_0",
- "4.1GB"
- ],
- [
- "7b-instruct-q4_1",
- "4.6GB"
- ],
- [
- "7b-instruct-q4_K_M",
- "4.4GB"
- ],
- [
- "7b-instruct-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-instruct-q5_0",
- "5.0GB"
- ],
- [
- "7b-instruct-q5_1",
- "5.4GB"
- ],
- [
- "7b-instruct-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-instruct-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-instruct-q6_K",
- "5.9GB"
- ],
- [
- "7b-instruct-q8_0",
- "7.7GB"
- ],
- [
- "7b-instruct-v0.2-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-instruct-v0.2-q5_0",
- "5.0GB"
- ],
- [
- "7b-instruct-v0.2-q4_0",
- "4.1GB"
- ],
- [
- "7b-instruct-v0.2-q5_1",
- "5.4GB"
- ],
[
"7b-instruct-v0.2-fp16",
"14GB"
],
- [
- "7b-instruct-v0.2-q3_K_L",
- "3.8GB"
- ],
[
"7b-instruct-v0.2-q2_K",
"3.1GB"
],
[
- "7b-instruct-v0.2-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-instruct-v0.2-q4_K_M",
- "4.4GB"
+ "7b-instruct-v0.2-q3_K_L",
+ "3.8GB"
],
[
"7b-instruct-v0.2-q3_K_M",
@@ -1599,10 +1647,34 @@
"7b-instruct-v0.2-q3_K_S",
"3.2GB"
],
+ [
+ "7b-instruct-v0.2-q4_0",
+ "4.1GB"
+ ],
[
"7b-instruct-v0.2-q4_1",
"4.6GB"
],
+ [
+ "7b-instruct-v0.2-q4_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-instruct-v0.2-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-instruct-v0.2-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-instruct-v0.2-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-instruct-v0.2-q5_K_M",
+ "5.1GB"
+ ],
[
"7b-instruct-v0.2-q5_K_S",
"5.0GB"
@@ -1671,10 +1743,70 @@
"7b-instruct-v0.3-q6_K",
"5.9GB"
],
+ [
+ "7b-instruct-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-instruct-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-instruct-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-instruct-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-instruct-fp16",
+ "14GB"
+ ],
+ [
+ "7b-instruct-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-instruct-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-instruct-q4_K_M",
+ "4.4GB"
+ ],
[
"7b-instruct-v0.3-q8_0",
"7.7GB"
],
+ [
+ "7b-instruct-q2_K",
+ "3.1GB"
+ ],
+ [
+ "7b-instruct-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-instruct-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-instruct-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-instruct-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-instruct-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-instruct-q8_0",
+ "7.7GB"
+ ],
[
"7b-text",
"4.1GB"
@@ -1716,48 +1848,48 @@
"3.2GB"
],
[
- "7b-text-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-text-q8_0",
- "7.7GB"
- ],
- [
- "7b-text-v0.2-q3_K_L",
- "3.8GB"
- ],
- [
- "7b-text-v0.2-q3_K_M",
- "3.5GB"
+ "7b-text-v0.2-fp16",
+ "14GB"
],
[
"7b-text-q5_0",
"5.0GB"
],
- [
- "7b-text-q4_K_S",
- "4.1GB"
- ],
[
"7b-text-q5_K_M",
"5.1GB"
],
+ [
+ "7b-text-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-text-q4_K_S",
+ "4.1GB"
+ ],
[
"7b-text-v0.2-q2_K",
"2.7GB"
],
+ [
+ "7b-text-v0.2-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-text-v0.2-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-text-q8_0",
+ "7.7GB"
+ ],
[
"7b-text-q6_K",
"5.9GB"
],
[
- "7b-text-v0.2-fp16",
- "14GB"
- ],
- [
- "7b-text-q5_1",
- "5.4GB"
+ "7b-text-q5_K_S",
+ "5.0GB"
],
[
"7b-text-v0.2-q4_0",
@@ -1811,14 +1943,14 @@
"latest",
"26GB"
],
- [
- "8x7b",
- "26GB"
- ],
[
"8x22b",
"80GB"
],
+ [
+ "8x7b",
+ "26GB"
+ ],
[
"instruct",
"26GB"
@@ -2179,101 +2311,41 @@
"7b-instruct",
"5.0GB"
],
- [
- "7b-instruct-fp16",
- "17GB"
- ],
- [
- "7b-instruct-q2_K",
- "3.5GB"
- ],
- [
- "7b-instruct-q3_K_L",
- "4.7GB"
- ],
- [
- "7b-instruct-q3_K_M",
- "4.4GB"
- ],
- [
- "7b-instruct-v1.1-q4_K_M",
- "5.3GB"
- ],
- [
- "7b-instruct-q5_K_M",
- "6.1GB"
- ],
- [
- "7b-instruct-v1.1-q4_1",
- "5.5GB"
- ],
- [
- "7b-instruct-v1.1-q4_0",
- "5.0GB"
- ],
- [
- "7b-instruct-q4_1",
- "5.5GB"
- ],
- [
- "7b-instruct-q6_K",
- "7.0GB"
- ],
- [
- "7b-instruct-q4_K_M",
- "5.3GB"
- ],
- [
- "7b-instruct-q3_K_S",
- "4.0GB"
- ],
- [
- "7b-instruct-q8_0",
- "9.1GB"
- ],
- [
- "7b-instruct-q4_K_S",
- "5.0GB"
- ],
- [
- "7b-instruct-v1.1-q3_K_L",
- "4.7GB"
- ],
- [
- "7b-instruct-q5_K_S",
- "6.0GB"
- ],
- [
- "7b-instruct-q5_0",
- "6.0GB"
- ],
[
"7b-instruct-v1.1-fp16",
"17GB"
],
- [
- "7b-instruct-v1.1-q3_K_S",
- "4.0GB"
- ],
[
"7b-instruct-v1.1-q2_K",
"3.5GB"
],
+ [
+ "7b-instruct-v1.1-q3_K_L",
+ "4.7GB"
+ ],
[
"7b-instruct-v1.1-q3_K_M",
"4.4GB"
],
[
- "7b-instruct-q4_0",
+ "7b-instruct-v1.1-q3_K_S",
+ "4.0GB"
+ ],
+ [
+ "7b-instruct-v1.1-q4_0",
"5.0GB"
],
[
- "7b-instruct-q5_1",
- "6.5GB"
+ "7b-instruct-v1.1-q4_1",
+ "5.5GB"
],
[
- "7b-instruct-v1.1-q8_0",
- "9.1GB"
+ "7b-instruct-v1.1-q4_K_M",
+ "5.3GB"
+ ],
+ [
+ "7b-instruct-v1.1-q4_K_S",
+ "5.0GB"
],
[
"7b-instruct-v1.1-q5_0",
@@ -2283,6 +2355,10 @@
"7b-instruct-v1.1-q5_1",
"6.5GB"
],
+ [
+ "7b-instruct-v1.1-q5_K_M",
+ "6.1GB"
+ ],
[
"7b-instruct-v1.1-q5_K_S",
"6.0GB"
@@ -2292,12 +2368,68 @@
"7.0GB"
],
[
- "7b-instruct-v1.1-q5_K_M",
+ "7b-instruct-q4_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-instruct-q4_0",
+ "5.0GB"
+ ],
+ [
+ "7b-instruct-q3_K_L",
+ "4.7GB"
+ ],
+ [
+ "7b-instruct-q4_K_M",
+ "5.3GB"
+ ],
+ [
+ "7b-instruct-q3_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-instruct-fp16",
+ "17GB"
+ ],
+ [
+ "7b-instruct-q2_K",
+ "3.5GB"
+ ],
+ [
+ "7b-instruct-q3_K_S",
+ "4.0GB"
+ ],
+ [
+ "7b-instruct-v1.1-q8_0",
+ "9.1GB"
+ ],
+ [
+ "7b-instruct-q4_1",
+ "5.5GB"
+ ],
+ [
+ "7b-instruct-q5_0",
+ "6.0GB"
+ ],
+ [
+ "7b-instruct-q5_1",
+ "6.5GB"
+ ],
+ [
+ "7b-instruct-q5_K_M",
"6.1GB"
],
[
- "7b-instruct-v1.1-q4_K_S",
- "5.0GB"
+ "7b-instruct-q5_K_S",
+ "6.0GB"
+ ],
+ [
+ "7b-instruct-q6_K",
+ "7.0GB"
+ ],
+ [
+ "7b-instruct-q8_0",
+ "9.1GB"
],
[
"7b-v1.1",
@@ -2336,48 +2468,28 @@
"1.7GB"
],
[
- "2b-code-q4_K_M",
+ "2b-code-v1.1-q4_K_M",
"1.6GB"
],
[
- "2b-code-q3_K_L",
- "1.5GB"
+ "2b-code-v1.1-q4_K_S",
+ "1.6GB"
],
[
- "2b-code-q3_K_M",
- "1.4GB"
- ],
- [
- "2b-code-v1.1-q6_K",
- "2.1GB"
- ],
- [
- "2b-code-v1.1-q5_K_S",
+ "2b-code-v1.1-q5_0",
"1.8GB"
],
- [
- "2b-code-q4_1",
- "1.7GB"
- ],
[
"2b-code-v1.1-q5_1",
"1.9GB"
],
- [
- "2b-code-v1.1-q4_K_M",
- "1.6GB"
- ],
[
"2b-code-v1.1-q5_K_M",
"1.8GB"
],
[
- "2b-code-q4_0",
- "1.6GB"
- ],
- [
- "2b-code-v1.1-q8_0",
- "2.7GB"
+ "2b-code-q4_1",
+ "1.7GB"
],
[
"2b-code-q3_K_S",
@@ -2387,17 +2499,37 @@
"2b-code-fp16",
"5.0GB"
],
+ [
+ "2b-code-v1.1-q6_K",
+ "2.1GB"
+ ],
[
"2b-code-q2_K",
"1.2GB"
],
[
- "2b-code-v1.1-q4_K_S",
+ "2b-code-q3_K_L",
+ "1.5GB"
+ ],
+ [
+ "2b-code-q3_K_M",
+ "1.4GB"
+ ],
+ [
+ "2b-code-v1.1-q8_0",
+ "2.7GB"
+ ],
+ [
+ "2b-code-v1.1-q5_K_S",
+ "1.8GB"
+ ],
+ [
+ "2b-code-q4_0",
"1.6GB"
],
[
- "2b-code-v1.1-q5_0",
- "1.8GB"
+ "2b-code-q4_K_M",
+ "1.6GB"
],
[
"2b-code-q4_K_S",
@@ -2976,80 +3108,12 @@
"5.0GB"
],
[
- "7b-instruct-fp16",
+ "7b-instruct-v1.1-fp16",
"17GB"
],
[
- "7b-instruct-q2_K",
- "3.7GB"
- ],
- [
- "7b-instruct-q3_K_L",
- "4.9GB"
- ],
- [
- "7b-instruct-q3_K_M",
- "4.6GB"
- ],
- [
- "7b-instruct-q3_K_S",
- "4.2GB"
- ],
- [
- "7b-instruct-q4_0",
- "5.2GB"
- ],
- [
- "7b-instruct-q4_1",
- "5.7GB"
- ],
- [
- "7b-instruct-q4_K_M",
- "5.5GB"
- ],
- [
- "7b-instruct-q4_K_S",
- "5.2GB"
- ],
- [
- "7b-instruct-q5_0",
- "6.2GB"
- ],
- [
- "7b-instruct-q5_1",
- "6.7GB"
- ],
- [
- "7b-instruct-q5_K_M",
- "6.3GB"
- ],
- [
- "7b-instruct-q5_K_S",
- "6.2GB"
- ],
- [
- "7b-instruct-q6_K",
- "7.2GB"
- ],
- [
- "7b-instruct-v1.1-q5_K_S",
- "6.0GB"
- ],
- [
- "7b-instruct-v1.1-q3_K_S",
- "4.0GB"
- ],
- [
- "7b-instruct-v1.1-q5_1",
- "6.5GB"
- ],
- [
- "7b-instruct-v1.1-q4_1",
- "5.5GB"
- ],
- [
- "7b-instruct-v1.1-q4_K_S",
- "5.0GB"
+ "7b-instruct-v1.1-q2_K",
+ "3.5GB"
],
[
"7b-instruct-v1.1-q3_K_L",
@@ -3060,41 +3124,109 @@
"4.4GB"
],
[
- "7b-instruct-v1.1-q5_0",
- "6.0GB"
+ "7b-instruct-v1.1-q3_K_S",
+ "4.0GB"
],
[
"7b-instruct-v1.1-q4_0",
"5.0GB"
],
- [
- "7b-instruct-v1.1-q4_K_M",
- "5.3GB"
- ],
- [
- "7b-instruct-v1.1-q5_K_M",
- "6.1GB"
- ],
[
"7b-instruct-q8_0",
"9.1GB"
],
[
- "7b-instruct-v1.1-q2_K",
- "3.5GB"
+ "7b-instruct-v1.1-q5_1",
+ "6.5GB"
],
[
- "7b-instruct-v1.1-fp16",
+ "7b-instruct-q3_K_L",
+ "4.9GB"
+ ],
+ [
+ "7b-instruct-fp16",
"17GB"
],
+ [
+ "7b-instruct-q5_0",
+ "6.2GB"
+ ],
[
"7b-instruct-v1.1-q6_K",
"7.0GB"
],
+ [
+ "7b-instruct-v1.1-q4_K_M",
+ "5.3GB"
+ ],
+ [
+ "7b-instruct-q3_K_S",
+ "4.2GB"
+ ],
+ [
+ "7b-instruct-q4_1",
+ "5.7GB"
+ ],
+ [
+ "7b-instruct-v1.1-q4_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-instruct-q3_K_M",
+ "4.6GB"
+ ],
+ [
+ "7b-instruct-q6_K",
+ "7.2GB"
+ ],
+ [
+ "7b-instruct-v1.1-q4_1",
+ "5.5GB"
+ ],
+ [
+ "7b-instruct-q2_K",
+ "3.7GB"
+ ],
+ [
+ "7b-instruct-v1.1-q5_K_S",
+ "6.0GB"
+ ],
+ [
+ "7b-instruct-q4_K_M",
+ "5.5GB"
+ ],
+ [
+ "7b-instruct-q4_K_S",
+ "5.2GB"
+ ],
+ [
+ "7b-instruct-q5_1",
+ "6.7GB"
+ ],
[
"7b-instruct-v1.1-q8_0",
"9.1GB"
],
+ [
+ "7b-instruct-v1.1-q5_K_M",
+ "6.1GB"
+ ],
+ [
+ "7b-instruct-q4_0",
+ "5.2GB"
+ ],
+ [
+ "7b-instruct-v1.1-q5_0",
+ "6.0GB"
+ ],
+ [
+ "7b-instruct-q5_K_S",
+ "6.2GB"
+ ],
+ [
+ "7b-instruct-q5_K_M",
+ "6.3GB"
+ ],
[
"7b-text",
"5.2GB"
@@ -3167,81 +3299,21 @@
"2b-instruct",
"1.6GB"
],
- [
- "2b-instruct-fp16",
- "4.5GB"
- ],
- [
- "2b-instruct-q2_K",
- "1.3GB"
- ],
- [
- "2b-instruct-q3_K_L",
- "1.6GB"
- ],
- [
- "2b-instruct-q3_K_M",
- "1.5GB"
- ],
- [
- "2b-instruct-q3_K_S",
- "1.4GB"
- ],
- [
- "2b-instruct-q4_0",
- "1.7GB"
- ],
- [
- "2b-instruct-q4_1",
- "1.8GB"
- ],
- [
- "2b-instruct-q4_K_M",
- "1.8GB"
- ],
- [
- "2b-instruct-q4_K_S",
- "1.7GB"
- ],
- [
- "2b-instruct-q5_0",
- "1.9GB"
- ],
- [
- "2b-instruct-q5_1",
- "2.1GB"
- ],
- [
- "2b-instruct-q5_K_M",
- "2.0GB"
- ],
[
"2b-instruct-v1.1-fp16",
"5.0GB"
],
[
- "2b-instruct-q8_0",
- "2.7GB"
- ],
- [
- "2b-instruct-q6_K",
- "2.2GB"
- ],
- [
- "2b-instruct-q5_K_S",
- "1.9GB"
- ],
- [
- "2b-instruct-v1.1-q3_K_M",
- "1.4GB"
+ "2b-instruct-v1.1-q2_K",
+ "1.2GB"
],
[
"2b-instruct-v1.1-q3_K_L",
"1.5GB"
],
[
- "2b-instruct-v1.1-q2_K",
- "1.2GB"
+ "2b-instruct-v1.1-q3_K_M",
+ "1.4GB"
],
[
"2b-instruct-v1.1-q3_K_S",
@@ -3287,6 +3359,66 @@
"2b-instruct-v1.1-q8_0",
"2.7GB"
],
+ [
+ "2b-instruct-q6_K",
+ "2.2GB"
+ ],
+ [
+ "2b-instruct-q5_K_S",
+ "1.9GB"
+ ],
+ [
+ "2b-instruct-q5_1",
+ "2.1GB"
+ ],
+ [
+ "2b-instruct-q4_K_S",
+ "1.7GB"
+ ],
+ [
+ "2b-instruct-q3_K_L",
+ "1.6GB"
+ ],
+ [
+ "2b-instruct-q5_0",
+ "1.9GB"
+ ],
+ [
+ "2b-instruct-q4_1",
+ "1.8GB"
+ ],
+ [
+ "2b-instruct-q5_K_M",
+ "2.0GB"
+ ],
+ [
+ "2b-instruct-q2_K",
+ "1.3GB"
+ ],
+ [
+ "2b-instruct-fp16",
+ "4.5GB"
+ ],
+ [
+ "2b-instruct-q4_0",
+ "1.7GB"
+ ],
+ [
+ "2b-instruct-q4_K_M",
+ "1.8GB"
+ ],
+ [
+ "2b-instruct-q3_K_M",
+ "1.5GB"
+ ],
+ [
+ "2b-instruct-q3_K_S",
+ "1.4GB"
+ ],
+ [
+ "2b-instruct-q8_0",
+ "2.7GB"
+ ],
[
"2b-text",
"1.7GB"
@@ -3528,48 +3660,108 @@
"41GB"
],
[
- "72b-chat-fp16",
+ "72b-chat-v1.5-fp16",
"145GB"
],
[
- "72b-chat-q2_K",
- "27GB"
+ "72b-chat-v1.5-q2_K",
+ "28GB"
],
[
- "72b-chat-q3_K_L",
- "39GB"
+ "72b-chat-v1.5-q3_K_L",
+ "38GB"
],
[
- "72b-chat-q3_K_M",
- "37GB"
+ "72b-chat-v1.5-q3_K_M",
+ "36GB"
+ ],
+ [
+ "72b-chat-v1.5-q3_K_S",
+ "33GB"
+ ],
+ [
+ "72b-chat-v1.5-q4_0",
+ "41GB"
+ ],
+ [
+ "72b-chat-v1.5-q4_1",
+ "45GB"
+ ],
+ [
+ "72b-chat-v1.5-q4_K_M",
+ "44GB"
+ ],
+ [
+ "72b-chat-v1.5-q4_K_S",
+ "42GB"
+ ],
+ [
+ "72b-chat-q5_1",
+ "54GB"
+ ],
+ [
+ "72b-chat-v1.5-q8_0",
+ "77GB"
],
[
"72b-chat-q3_K_S",
"32GB"
],
[
- "72b-chat-q4_0",
- "41GB"
+ "72b-chat-q3_K_L",
+ "39GB"
],
[
"72b-chat-q4_1",
"45GB"
],
[
- "72b-chat-q4_K_M",
- "45GB"
+ "72b-chat-v1.5-q6_K",
+ "59GB"
],
[
- "72b-chat-q4_K_S",
+ "72b-chat-v1.5-q5_K_S",
+ "50GB"
+ ],
+ [
+ "72b-chat-q4_0",
"41GB"
],
+ [
+ "72b-chat-v1.5-q5_1",
+ "54GB"
+ ],
+ [
+ "72b-chat-v1.5-q5_K_M",
+ "51GB"
+ ],
[
"72b-chat-q5_0",
"50GB"
],
[
- "72b-chat-q5_1",
- "54GB"
+ "72b-chat-q2_K",
+ "27GB"
+ ],
+ [
+ "72b-chat-q4_K_M",
+ "45GB"
+ ],
+ [
+ "72b-chat-fp16",
+ "145GB"
+ ],
+ [
+ "72b-chat-q3_K_M",
+ "37GB"
+ ],
+ [
+ "72b-chat-v1.5-q5_0",
+ "50GB"
+ ],
+ [
+ "72b-chat-q4_K_S",
+ "41GB"
],
[
"72b-chat-q5_K_M",
@@ -3583,70 +3775,10 @@
"72b-chat-q6_K",
"59GB"
],
- [
- "72b-chat-v1.5-q4_K_M",
- "44GB"
- ],
- [
- "72b-chat-v1.5-q2_K",
- "28GB"
- ],
- [
- "72b-chat-v1.5-q4_0",
- "41GB"
- ],
- [
- "72b-chat-v1.5-q4_1",
- "45GB"
- ],
- [
- "72b-chat-v1.5-q3_K_L",
- "38GB"
- ],
[
"72b-chat-q8_0",
"77GB"
],
- [
- "72b-chat-v1.5-q3_K_M",
- "36GB"
- ],
- [
- "72b-chat-v1.5-q3_K_S",
- "33GB"
- ],
- [
- "72b-chat-v1.5-fp16",
- "145GB"
- ],
- [
- "72b-chat-v1.5-q4_K_S",
- "42GB"
- ],
- [
- "72b-chat-v1.5-q5_0",
- "50GB"
- ],
- [
- "72b-chat-v1.5-q5_1",
- "54GB"
- ],
- [
- "72b-chat-v1.5-q5_K_M",
- "51GB"
- ],
- [
- "72b-chat-v1.5-q5_K_S",
- "50GB"
- ],
- [
- "72b-chat-v1.5-q6_K",
- "59GB"
- ],
- [
- "72b-chat-v1.5-q8_0",
- "77GB"
- ],
[
"72b-text",
"63GB"
@@ -3667,89 +3799,89 @@
"72b-text-v1.5-q3_K_M",
"36GB"
],
- [
- "72b-text-q4_1",
- "45GB"
- ],
- [
- "72b-text-v1.5-q5_K_M",
- "51GB"
- ],
- [
- "72b-text-fp16",
- "145GB"
- ],
- [
- "72b-text-q4_0",
- "41GB"
- ],
- [
- "72b-text-v1.5-q4_K_M",
- "44GB"
- ],
- [
- "72b-text-v1.5-q5_1",
- "54GB"
- ],
- [
- "72b-text-v1.5-q8_0",
- "77GB"
- ],
- [
- "72b-text-q3_K_S",
- "32GB"
- ],
- [
- "72b-text-q3_K_M",
- "37GB"
- ],
- [
- "72b-text-v1.5-q4_K_S",
- "42GB"
- ],
- [
- "72b-text-v1.5-q4_1",
- "45GB"
- ],
- [
- "72b-text-q3_K_L",
- "39GB"
- ],
[
"72b-text-v1.5-q3_K_S",
"33GB"
],
- [
- "72b-text-v1.5-q5_0",
- "50GB"
- ],
- [
- "72b-text-v1.5-q6_K",
- "59GB"
- ],
[
"72b-text-v1.5-q4_0",
"41GB"
],
[
- "72b-text-q2_K",
- "27GB"
+ "72b-text-v1.5-q4_1",
+ "45GB"
+ ],
+ [
+ "72b-text-v1.5-q4_K_M",
+ "44GB"
+ ],
+ [
+ "72b-text-v1.5-q4_K_S",
+ "42GB"
+ ],
+ [
+ "72b-text-v1.5-q5_0",
+ "50GB"
+ ],
+ [
+ "72b-text-v1.5-q5_1",
+ "54GB"
+ ],
+ [
+ "72b-text-v1.5-q5_K_M",
+ "51GB"
],
[
"72b-text-v1.5-q5_K_S",
"50GB"
],
[
- "72b-text-q4_K_M",
- "45GB"
+ "72b-text-q5_0",
+ "50GB"
+ ],
+ [
+ "72b-text-q3_K_L",
+ "39GB"
+ ],
+ [
+ "72b-text-q2_K",
+ "27GB"
],
[
"72b-text-q4_K_S",
"41GB"
],
[
- "72b-text-q5_0",
- "50GB"
+ "72b-text-v1.5-q6_K",
+ "59GB"
+ ],
+ [
+ "72b-text-q4_0",
+ "41GB"
+ ],
+ [
+ "72b-text-q3_K_M",
+ "37GB"
+ ],
+ [
+ "72b-text-q3_K_S",
+ "32GB"
+ ],
+ [
+ "72b-text-v1.5-q8_0",
+ "77GB"
+ ],
+ [
+ "72b-text-fp16",
+ "145GB"
+ ],
+ [
+ "72b-text-q4_1",
+ "45GB"
+ ],
+ [
+ "72b-text-q4_K_M",
+ "45GB"
],
[
"72b-text-q5_1",
@@ -3936,16 +4068,16 @@
"10GB"
],
[
- "14b-chat-v1.5-q6_K",
- "12GB"
+ "14b-chat-q4_1",
+ "9.0GB"
],
[
- "14b-chat-v1.5-q8_0",
- "15GB"
+ "14b-chat-q3_K_L",
+ "8.0GB"
],
[
- "14b-chat-q8_0",
- "15GB"
+ "14b-chat-q4_0",
+ "8.2GB"
],
[
"14b-chat-q3_K_S",
@@ -3956,103 +4088,87 @@
"28GB"
],
[
- "14b-chat-q4_K_S",
- "8.6GB"
+ "14b-chat-v1.5-q8_0",
+ "15GB"
],
[
- "14b-chat-q5_K_M",
- "11GB"
- ],
- [
- "14b-chat-q4_1",
- "9.0GB"
- ],
- [
- "14b-chat-q6_K",
+ "14b-chat-v1.5-q6_K",
"12GB"
],
- [
- "14b-chat-q3_K_L",
- "8.0GB"
- ],
- [
- "14b-chat-q5_0",
- "9.9GB"
- ],
- [
- "14b-chat-q3_K_M",
- "7.7GB"
- ],
- [
- "14b-chat-q5_1",
- "11GB"
- ],
- [
- "14b-chat-q4_0",
- "8.2GB"
- ],
[
"14b-chat-q2_K",
"6.0GB"
],
+ [
+ "14b-chat-q3_K_M",
+ "7.7GB"
+ ],
[
"14b-chat-q4_K_M",
"9.4GB"
],
+ [
+ "14b-chat-q4_K_S",
+ "8.6GB"
+ ],
+ [
+ "14b-chat-q5_0",
+ "9.9GB"
+ ],
+ [
+ "14b-chat-q5_1",
+ "11GB"
+ ],
+ [
+ "14b-chat-q5_K_M",
+ "11GB"
+ ],
[
"14b-chat-q5_K_S",
"10GB"
],
[
- "14b-text",
- "8.2GB"
- ],
- [
- "14b-text-v1.5-fp16",
- "28GB"
- ],
- [
- "14b-text-v1.5-q2_K",
- "6.1GB"
- ],
- [
- "14b-text-v1.5-q3_K_L",
- "7.8GB"
- ],
- [
- "14b-text-q3_K_L",
- "8.0GB"
- ],
- [
- "14b-text-v1.5-q8_0",
- "15GB"
- ],
- [
- "14b-text-v1.5-q4_0",
- "8.2GB"
- ],
- [
- "14b-text-v1.5-q6_K",
+ "14b-chat-q6_K",
"12GB"
],
[
- "14b-text-v1.5-q4_1",
- "9.0GB"
+ "14b-chat-q8_0",
+ "15GB"
],
[
- "14b-text-v1.5-q4_K_M",
- "9.2GB"
- ],
- [
- "14b-text-v1.5-q5_K_S",
- "10GB"
+ "14b-text",
+ "8.2GB"
],
[
"14b-text-fp16",
"28GB"
],
[
- "14b-text-v1.5-q5_1",
+ "14b-text-q2_K",
+ "6.0GB"
+ ],
+ [
+ "14b-text-q3_K_L",
+ "8.0GB"
+ ],
+ [
+ "14b-text-q3_K_M",
+ "7.7GB"
+ ],
+ [
+ "14b-text-q3_K_S",
+ "6.9GB"
+ ],
+ [
+ "14b-text-v1.5-q4_K_M",
+ "9.2GB"
+ ],
+ [
+ "14b-text-q4_0",
+ "8.2GB"
+ ],
+ [
+ "14b-text-q5_1",
"11GB"
],
[
@@ -4060,23 +4176,7 @@
"6.9GB"
],
[
- "14b-text-v1.5-q5_0",
- "9.9GB"
- ],
- [
- "14b-text-v1.5-q4_K_S",
- "8.6GB"
- ],
- [
- "14b-text-v1.5-q3_K_M",
- "7.4GB"
- ],
- [
- "14b-text-q2_K",
- "6.0GB"
- ],
- [
- "14b-text-v1.5-q5_K_M",
+ "14b-text-q5_K_M",
"11GB"
],
[
@@ -4084,41 +4184,9 @@
"10GB"
],
[
- "14b-text-q3_K_S",
- "6.9GB"
- ],
- [
- "14b-text-q4_1",
- "9.0GB"
- ],
- [
- "14b-text-q4_0",
+ "14b-text-v1.5-q4_0",
"8.2GB"
],
- [
- "14b-text-q3_K_M",
- "7.7GB"
- ],
- [
- "14b-text-q4_K_S",
- "8.6GB"
- ],
- [
- "14b-text-q5_0",
- "9.9GB"
- ],
- [
- "14b-text-q5_K_M",
- "11GB"
- ],
- [
- "14b-text-q4_K_M",
- "9.4GB"
- ],
- [
- "14b-text-q5_1",
- "11GB"
- ],
[
"14b-text-q6_K",
"12GB"
@@ -4128,81 +4196,85 @@
"15GB"
],
[
- "7b-chat",
- "4.5GB"
+ "14b-text-q5_0",
+ "9.9GB"
],
[
- "7b-chat-v1.5-fp16",
+ "14b-text-q4_1",
+ "9.0GB"
+ ],
+ [
+ "14b-text-v1.5-q4_1",
+ "9.0GB"
+ ],
+ [
+ "14b-text-q4_K_S",
+ "8.6GB"
+ ],
+ [
+ "14b-text-q4_K_M",
+ "9.4GB"
+ ],
+ [
+ "14b-text-v1.5-q3_K_L",
+ "7.8GB"
+ ],
+ [
+ "14b-text-v1.5-q3_K_M",
+ "7.4GB"
+ ],
+ [
+ "14b-text-v1.5-fp16",
+ "28GB"
+ ],
+ [
+ "14b-text-v1.5-q2_K",
+ "6.1GB"
+ ],
+ [
+ "14b-text-v1.5-q4_K_S",
+ "8.6GB"
+ ],
+ [
+ "14b-text-v1.5-q5_0",
+ "9.9GB"
+ ],
+ [
+ "14b-text-v1.5-q5_1",
+ "11GB"
+ ],
+ [
+ "14b-text-v1.5-q5_K_M",
+ "11GB"
+ ],
+ [
+ "14b-text-v1.5-q5_K_S",
+ "10GB"
+ ],
+ [
+ "14b-text-v1.5-q6_K",
+ "12GB"
+ ],
+ [
+ "14b-text-v1.5-q8_0",
"15GB"
],
[
- "7b-chat-v1.5-q2_K",
- "3.1GB"
- ],
- [
- "7b-chat-v1.5-q3_K_L",
- "4.2GB"
- ],
- [
- "7b-chat-v1.5-q3_K_M",
- "3.9GB"
- ],
- [
- "7b-chat-v1.5-q3_K_S",
- "3.6GB"
- ],
- [
- "7b-chat-v1.5-q4_0",
+ "7b-chat",
"4.5GB"
],
- [
- "7b-chat-v1.5-q4_1",
- "5.0GB"
- ],
- [
- "7b-chat-v1.5-q4_K_M",
- "4.8GB"
- ],
- [
- "7b-chat-v1.5-q4_K_S",
- "4.5GB"
- ],
- [
- "7b-chat-v1.5-q5_0",
- "5.4GB"
- ],
- [
- "7b-chat-v1.5-q5_1",
- "5.8GB"
- ],
- [
- "7b-chat-v1.5-q5_K_M",
- "5.5GB"
- ],
- [
- "7b-chat-v1.5-q5_K_S",
- "5.4GB"
- ],
- [
- "7b-chat-v1.5-q6_K",
- "6.3GB"
- ],
- [
- "7b-chat-q3_K_L",
- "4.3GB"
- ],
[
"7b-chat-fp16",
"15GB"
],
- [
- "7b-chat-v1.5-q8_0",
- "8.2GB"
- ],
[
"7b-chat-q2_K",
"3.0GB"
],
+ [
+ "7b-chat-q3_K_L",
+ "4.3GB"
+ ],
[
"7b-chat-q3_K_M",
"4.1GB"
@@ -4220,35 +4292,95 @@
"5.0GB"
],
[
- "7b-chat-q4_K_M",
- "4.9GB"
+ "7b-chat-v1.5-q5_1",
+ "5.8GB"
],
[
- "7b-chat-q4_K_S",
- "4.5GB"
- ],
- [
- "7b-chat-q5_0",
- "5.4GB"
+ "7b-chat-v1.5-q3_K_M",
+ "3.9GB"
],
[
"7b-chat-q5_1",
"5.8GB"
],
+ [
+ "7b-chat-q4_K_S",
+ "4.5GB"
+ ],
[
"7b-chat-q5_K_M",
"5.7GB"
],
+ [
+ "7b-chat-q4_K_M",
+ "4.9GB"
+ ],
+ [
+ "7b-chat-q8_0",
+ "8.2GB"
+ ],
+ [
+ "7b-chat-v1.5-q4_1",
+ "5.0GB"
+ ],
+ [
+ "7b-chat-v1.5-q4_K_S",
+ "4.5GB"
+ ],
+ [
+ "7b-chat-v1.5-q2_K",
+ "3.1GB"
+ ],
+ [
+ "7b-chat-v1.5-q3_K_S",
+ "3.6GB"
+ ],
[
"7b-chat-q5_K_S",
"5.4GB"
],
+ [
+ "7b-chat-v1.5-q4_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-chat-v1.5-q5_0",
+ "5.4GB"
+ ],
[
"7b-chat-q6_K",
"6.3GB"
],
[
- "7b-chat-q8_0",
+ "7b-chat-q5_0",
+ "5.4GB"
+ ],
+ [
+ "7b-chat-v1.5-q4_0",
+ "4.5GB"
+ ],
+ [
+ "7b-chat-v1.5-q3_K_L",
+ "4.2GB"
+ ],
+ [
+ "7b-chat-v1.5-fp16",
+ "15GB"
+ ],
+ [
+ "7b-chat-v1.5-q5_K_M",
+ "5.5GB"
+ ],
+ [
+ "7b-chat-v1.5-q5_K_S",
+ "5.4GB"
+ ],
+ [
+ "7b-chat-v1.5-q6_K",
+ "6.3GB"
+ ],
+ [
+ "7b-chat-v1.5-q8_0",
"8.2GB"
],
[
@@ -4508,29 +4640,33 @@
"1.1GB"
],
[
- "1.8b-chat-v1.5-fp16",
+ "1.8b-chat-fp16",
"3.7GB"
],
[
- "1.8b-chat-v1.5-q2_K",
- "863MB"
+ "1.8b-chat-q2_K",
+ "853MB"
],
[
- "1.8b-chat-v1.5-q3_K_L",
+ "1.8b-chat-q3_K_L",
"1.1GB"
],
[
- "1.8b-chat-v1.5-q3_K_M",
+ "1.8b-chat-q3_K_M",
"1.0GB"
],
[
- "1.8b-chat-v1.5-q3_K_S",
+ "1.8b-chat-q3_K_S",
"970MB"
],
[
- "1.8b-chat-v1.5-q4_0",
+ "1.8b-chat-q4_0",
"1.1GB"
],
+ [
+ "1.8b-chat-v1.5-q4_K_S",
+ "1.2GB"
+ ],
[
"1.8b-chat-v1.5-q4_1",
"1.2GB"
@@ -4540,127 +4676,135 @@
"1.2GB"
],
[
- "1.8b-chat-v1.5-q4_K_S",
- "1.2GB"
- ],
- [
- "1.8b-chat-q3_K_S",
+ "1.8b-chat-v1.5-q3_K_S",
"970MB"
],
+ [
+ "1.8b-chat-q4_1",
+ "1.2GB"
+ ],
+ [
+ "1.8b-chat-v1.5-fp16",
+ "3.7GB"
+ ],
+ [
+ "1.8b-chat-v1.5-q3_K_L",
+ "1.1GB"
+ ],
+ [
+ "1.8b-chat-v1.5-q3_K_M",
+ "1.0GB"
+ ],
+ [
+ "1.8b-chat-v1.5-q4_0",
+ "1.1GB"
+ ],
+ [
+ "1.8b-chat-q4_K_S",
+ "1.2GB"
+ ],
+ [
+ "1.8b-chat-q5_K_M",
+ "1.4GB"
+ ],
+ [
+ "1.8b-chat-q5_1",
+ "1.4GB"
+ ],
+ [
+ "1.8b-chat-q8_0",
+ "2.0GB"
+ ],
+ [
+ "1.8b-chat-q4_K_M",
+ "1.2GB"
+ ],
+ [
+ "1.8b-chat-v1.5-q2_K",
+ "863MB"
+ ],
+ [
+ "1.8b-chat-q6_K",
+ "1.6GB"
+ ],
+ [
+ "1.8b-chat-q5_K_S",
+ "1.3GB"
+ ],
+ [
+ "1.8b-chat-q5_0",
+ "1.3GB"
+ ],
[
"1.8b-chat-v1.5-q5_0",
"1.3GB"
],
+ [
+ "1.8b-chat-v1.5-q5_1",
+ "1.4GB"
+ ],
+ [
+ "1.8b-chat-v1.5-q5_K_M",
+ "1.4GB"
+ ],
+ [
+ "1.8b-chat-v1.5-q5_K_S",
+ "1.3GB"
+ ],
[
"1.8b-chat-v1.5-q6_K",
"1.6GB"
],
- [
- "1.8b-chat-v1.5-q5_1",
- "1.4GB"
- ],
[
"1.8b-chat-v1.5-q8_0",
"2.0GB"
],
- [
- "1.8b-chat-v1.5-q5_K_S",
- "1.3GB"
- ],
- [
- "1.8b-chat-q3_K_L",
- "1.1GB"
- ],
- [
- "1.8b-chat-fp16",
- "3.7GB"
- ],
- [
- "1.8b-chat-v1.5-q5_K_M",
- "1.4GB"
- ],
- [
- "1.8b-chat-q2_K",
- "853MB"
- ],
- [
- "1.8b-chat-q3_K_M",
- "1.0GB"
- ],
- [
- "1.8b-chat-q4_0",
- "1.1GB"
- ],
- [
- "1.8b-chat-q4_1",
- "1.2GB"
- ],
- [
- "1.8b-chat-q4_K_M",
- "1.2GB"
- ],
- [
- "1.8b-chat-q4_K_S",
- "1.2GB"
- ],
- [
- "1.8b-chat-q5_0",
- "1.3GB"
- ],
- [
- "1.8b-chat-q5_1",
- "1.4GB"
- ],
- [
- "1.8b-chat-q5_K_M",
- "1.4GB"
- ],
- [
- "1.8b-chat-q5_K_S",
- "1.3GB"
- ],
- [
- "1.8b-chat-q6_K",
- "1.6GB"
- ],
- [
- "1.8b-chat-q8_0",
- "2.0GB"
- ],
[
"1.8b-text",
"1.1GB"
],
[
- "1.8b-text-fp16",
+ "1.8b-text-v1.5-fp16",
"3.7GB"
],
[
- "1.8b-text-q2_K",
- "853MB"
+ "1.8b-text-v1.5-q2_K",
+ "863MB"
],
[
- "1.8b-text-q3_K_L",
+ "1.8b-text-v1.5-q3_K_L",
"1.1GB"
],
[
- "1.8b-text-q3_K_M",
+ "1.8b-text-v1.5-q3_K_M",
"1.0GB"
],
[
- "1.8b-text-q3_K_S",
+ "1.8b-text-v1.5-q3_K_S",
"970MB"
],
[
- "1.8b-text-q4_0",
+ "1.8b-text-v1.5-q4_0",
"1.1GB"
],
[
- "1.8b-text-q4_1",
+ "1.8b-text-v1.5-q4_1",
"1.2GB"
],
[
- "1.8b-text-q4_K_M",
+ "1.8b-text-v1.5-q4_K_M",
+ "1.2GB"
+ ],
+ [
+ "1.8b-text-v1.5-q4_K_S",
+ "1.2GB"
+ ],
+ [
+ "1.8b-text-q5_0",
+ "1.3GB"
+ ],
+ [
+ "1.8b-text-q4_1",
"1.2GB"
],
[
@@ -4668,7 +4812,55 @@
"1.2GB"
],
[
- "1.8b-text-q5_0",
+ "1.8b-text-q3_K_M",
+ "1.0GB"
+ ],
+ [
+ "1.8b-text-fp16",
+ "3.7GB"
+ ],
+ [
+ "1.8b-text-q3_K_L",
+ "1.1GB"
+ ],
+ [
+ "1.8b-text-q3_K_S",
+ "970MB"
+ ],
+ [
+ "1.8b-text-v1.5-q6_K",
+ "1.6GB"
+ ],
+ [
+ "1.8b-text-q4_0",
+ "1.1GB"
+ ],
+ [
+ "1.8b-text-v1.5-q5_K_M",
+ "1.4GB"
+ ],
+ [
+ "1.8b-text-v1.5-q5_K_S",
+ "1.3GB"
+ ],
+ [
+ "1.8b-text-q2_K",
+ "853MB"
+ ],
+ [
+ "1.8b-text-v1.5-q8_0",
+ "2.0GB"
+ ],
+ [
+ "1.8b-text-q4_K_M",
+ "1.2GB"
+ ],
+ [
+ "1.8b-text-v1.5-q5_1",
+ "1.4GB"
+ ],
+ [
+ "1.8b-text-v1.5-q5_0",
"1.3GB"
],
[
@@ -4687,70 +4879,10 @@
"1.8b-text-q6_K",
"1.6GB"
],
- [
- "1.8b-text-v1.5-q5_K_S",
- "1.3GB"
- ],
- [
- "1.8b-text-v1.5-q4_K_S",
- "1.2GB"
- ],
- [
- "1.8b-text-v1.5-q5_0",
- "1.3GB"
- ],
- [
- "1.8b-text-v1.5-q5_K_M",
- "1.4GB"
- ],
- [
- "1.8b-text-v1.5-q4_0",
- "1.1GB"
- ],
- [
- "1.8b-text-v1.5-q2_K",
- "863MB"
- ],
- [
- "1.8b-text-v1.5-q4_K_M",
- "1.2GB"
- ],
[
"1.8b-text-q8_0",
"2.0GB"
],
- [
- "1.8b-text-v1.5-q3_K_S",
- "970MB"
- ],
- [
- "1.8b-text-v1.5-q4_1",
- "1.2GB"
- ],
- [
- "1.8b-text-v1.5-q5_1",
- "1.4GB"
- ],
- [
- "1.8b-text-v1.5-q3_K_L",
- "1.1GB"
- ],
- [
- "1.8b-text-v1.5-fp16",
- "3.7GB"
- ],
- [
- "1.8b-text-v1.5-q3_K_M",
- "1.0GB"
- ],
- [
- "1.8b-text-v1.5-q6_K",
- "1.6GB"
- ],
- [
- "1.8b-text-v1.5-q8_0",
- "2.0GB"
- ],
[
"0.5b-chat",
"395MB"
@@ -6111,14 +6243,14 @@
"latest",
"26GB"
],
- [
- "8x7b",
- "26GB"
- ],
[
"8x22b",
"80GB"
],
+ [
+ "8x7b",
+ "26GB"
+ ],
[
"v2.5",
"26GB"
@@ -6459,6 +6591,26 @@
"image": false,
"author": "Eric Hartford"
},
+ "nomic-embed-text": {
+ "url": "https://ollama.com/library/nomic-embed-text",
+ "description": "A high-performing open embedding model with a large token context window.",
+ "tags": [
+ [
+ "latest",
+ "274MB"
+ ],
+ [
+ "v1.5",
+ "274MB"
+ ],
+ [
+ "137m-v1.5-fp16",
+ "274MB"
+ ]
+ ],
+ "image": false,
+ "author": "Nomic AI"
+ },
"llama2-uncensored": {
"url": "https://ollama.com/library/llama2-uncensored",
"description": "Uncensored Llama 2 model by George Sung and Jarrad Hope.",
@@ -7019,26 +7171,6 @@
"image": false,
"author": "DeepSeek Team"
},
- "nomic-embed-text": {
- "url": "https://ollama.com/library/nomic-embed-text",
- "description": "A high-performing open embedding model with a large token context window.",
- "tags": [
- [
- "latest",
- "274MB"
- ],
- [
- "v1.5",
- "274MB"
- ],
- [
- "137m-v1.5-fp16",
- "274MB"
- ]
- ],
- "image": false,
- "author": "Nomic AI"
- },
"phi": {
"url": "https://ollama.com/library/phi",
"description": "Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.",
@@ -7420,32 +7552,88 @@
"4.1GB"
],
[
- "7b-v2.6-fp16",
+ "7b-v2.6-dpo-laser-fp16",
"14GB"
],
+ [
+ "7b-v2.6-dpo-laser-q2_K",
+ "3.1GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q4_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q4_K_S",
+ "4.1GB"
+ ],
[
"7b-v2.6-q2_K",
"3.1GB"
],
[
- "7b-v2.6-q3_K_L",
- "3.8GB"
+ "7b-v2.6-dpo-laser-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-v2.6-fp16",
+ "14GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q8_0",
+ "7.7GB"
+ ],
+ [
+ "7b-v2.6-dpo-laser-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-v2.6-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-v2.6-q5_K_M",
+ "5.1GB"
],
[
"7b-v2.6-q3_K_M",
"3.5GB"
],
[
- "7b-v2.6-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-v2.6-q4_0",
- "4.1GB"
- ],
- [
- "7b-v2.6-q4_1",
- "4.6GB"
+ "7b-v2.6-q5_0",
+ "5.0GB"
],
[
"7b-v2.6-q4_K_M",
@@ -7456,89 +7644,33 @@
"4.1GB"
],
[
- "7b-v2.6-q5_0",
- "5.0GB"
+ "7b-v2.6-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-v2.6-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-v2.6-q4_1",
+ "4.6GB"
],
[
"7b-v2.6-q5_1",
"5.4GB"
],
[
- "7b-v2.6-q5_K_M",
- "5.1GB"
+ "7b-v2.6-q3_K_S",
+ "3.2GB"
],
[
"7b-v2.6-q5_K_S",
"5.0GB"
],
- [
- "7b-v2.6-q6_K",
- "5.9GB"
- ],
- [
- "7b-v2.6-dpo-laser-q4_K_M",
- "4.4GB"
- ],
- [
- "7b-v2.6-dpo-laser-q3_K_L",
- "3.8GB"
- ],
[
"7b-v2.6-q8_0",
"7.7GB"
],
- [
- "7b-v2.6-dpo-laser-q3_K_M",
- "3.5GB"
- ],
- [
- "7b-v2.6-dpo-laser-q2_K",
- "3.1GB"
- ],
- [
- "7b-v2.6-dpo-laser-q4_0",
- "4.1GB"
- ],
- [
- "7b-v2.6-dpo-laser-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-v2.6-dpo-laser-fp16",
- "14GB"
- ],
- [
- "7b-v2.6-dpo-laser-q4_1",
- "4.6GB"
- ],
- [
- "7b-v2.6-dpo-laser-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-v2.6-dpo-laser-q5_0",
- "5.0GB"
- ],
- [
- "7b-v2.6-dpo-laser-q5_1",
- "5.4GB"
- ],
- [
- "7b-v2.6-dpo-laser-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-v2.6-dpo-laser-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-v2.6-dpo-laser-q6_K",
- "5.9GB"
- ],
- [
- "7b-v2.6-dpo-laser-q8_0",
- "7.7GB"
- ],
[
"7b-v2.8",
"4.1GB"
@@ -7607,82 +7739,6 @@
"image": false,
"author": "Eric Hartford"
},
- "mistral-openorca": {
- "url": "https://ollama.com/library/mistral-openorca",
- "description": "Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.",
- "tags": [
- [
- "latest",
- "4.1GB"
- ],
- [
- "7b",
- "4.1GB"
- ],
- [
- "7b-fp16",
- "14GB"
- ],
- [
- "7b-q2_K",
- "3.1GB"
- ],
- [
- "7b-q3_K_L",
- "3.8GB"
- ],
- [
- "7b-q3_K_M",
- "3.5GB"
- ],
- [
- "7b-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-q4_0",
- "4.1GB"
- ],
- [
- "7b-q4_1",
- "4.6GB"
- ],
- [
- "7b-q4_K_M",
- "4.4GB"
- ],
- [
- "7b-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-q5_0",
- "5.0GB"
- ],
- [
- "7b-q5_1",
- "5.4GB"
- ],
- [
- "7b-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-q6_K",
- "5.9GB"
- ],
- [
- "7b-q8_0",
- "7.7GB"
- ]
- ],
- "image": false,
- "author": "Open Orca"
- },
"orca-mini": {
"url": "https://ollama.com/library/orca-mini",
"description": "A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.",
@@ -8167,30 +8223,6 @@
"image": false,
"author": "Orca Mini Team"
},
- "mxbai-embed-large": {
- "url": "https://ollama.com/library/mxbai-embed-large",
- "description": "State-of-the-art large embedding model from mixedbread.ai",
- "tags": [
- [
- "latest",
- "670MB"
- ],
- [
- "335m",
- "670MB"
- ],
- [
- "v1",
- "670MB"
- ],
- [
- "335m-v1-fp16",
- "670MB"
- ]
- ],
- "image": false,
- "author": "Mixedbread.ai"
- },
"dolphin-llama3": {
"url": "https://ollama.com/library/dolphin-llama3",
"description": "Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.",
@@ -8280,11 +8312,11 @@
"75GB"
],
[
- "8b-256k-v2.9",
+ "8b-256k",
"4.7GB"
],
[
- "8b-256k",
+ "8b-256k-v2.9",
"4.7GB"
],
[
@@ -8415,6 +8447,106 @@
"image": false,
"author": "Eric Hartford"
},
+ "mxbai-embed-large": {
+ "url": "https://ollama.com/library/mxbai-embed-large",
+ "description": "State-of-the-art large embedding model from mixedbread.ai",
+ "tags": [
+ [
+ "latest",
+ "670MB"
+ ],
+ [
+ "335m",
+ "670MB"
+ ],
+ [
+ "v1",
+ "670MB"
+ ],
+ [
+ "335m-v1-fp16",
+ "670MB"
+ ]
+ ],
+ "image": false,
+ "author": "Mixedbread.ai"
+ },
+ "mistral-openorca": {
+ "url": "https://ollama.com/library/mistral-openorca",
+ "description": "Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.",
+ "tags": [
+ [
+ "latest",
+ "4.1GB"
+ ],
+ [
+ "7b",
+ "4.1GB"
+ ],
+ [
+ "7b-fp16",
+ "14GB"
+ ],
+ [
+ "7b-q2_K",
+ "3.1GB"
+ ],
+ [
+ "7b-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-q4_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-q8_0",
+ "7.7GB"
+ ]
+ ],
+ "image": false,
+ "author": "Open Orca"
+ },
"starcoder2": {
"url": "https://ollama.com/library/starcoder2",
"description": "StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.",
@@ -8459,6 +8591,26 @@
"15b-instruct-v0.1-q3_K_M",
"8.0GB"
],
+ [
+ "15b-instruct-q4_0",
+ "9.1GB"
+ ],
+ [
+ "15b-instruct-v0.1-q4_K_S",
+ "9.2GB"
+ ],
+ [
+ "15b-instruct-v0.1-q4_1",
+ "10GB"
+ ],
+ [
+ "15b-instruct-v0.1-q5_0",
+ "11GB"
+ ],
+ [
+ "15b-instruct-v0.1-q8_0",
+ "17GB"
+ ],
[
"15b-instruct-v0.1-q3_K_S",
"7.0GB"
@@ -8468,20 +8620,16 @@
"9.1GB"
],
[
- "15b-instruct-v0.1-q4_1",
- "10GB"
+ "15b-instruct-v0.1-q5_K_S",
+ "11GB"
],
[
"15b-instruct-v0.1-q4_K_M",
"9.9GB"
],
[
- "15b-instruct-v0.1-q4_K_S",
- "9.2GB"
- ],
- [
- "15b-instruct-v0.1-q5_0",
- "11GB"
+ "15b-instruct-v0.1-q6_K",
+ "13GB"
],
[
"15b-instruct-v0.1-q5_1",
@@ -8491,22 +8639,6 @@
"15b-instruct-v0.1-q5_K_M",
"11GB"
],
- [
- "15b-instruct-v0.1-q5_K_S",
- "11GB"
- ],
- [
- "15b-instruct-v0.1-q6_K",
- "13GB"
- ],
- [
- "15b-instruct-v0.1-q8_0",
- "17GB"
- ],
- [
- "15b-instruct-q4_0",
- "9.1GB"
- ],
[
"15b-fp16",
"32GB"
@@ -8691,154 +8823,6 @@
"image": false,
"author": "BigCode"
},
- "llama2-chinese": {
- "url": "https://ollama.com/library/llama2-chinese",
- "description": "Llama 2 based model fine tuned to improve Chinese dialogue ability.",
- "tags": [
- [
- "latest",
- "3.8GB"
- ],
- [
- "13b",
- "7.4GB"
- ],
- [
- "7b",
- "3.8GB"
- ],
- [
- "13b-chat",
- "7.4GB"
- ],
- [
- "13b-chat-fp16",
- "26GB"
- ],
- [
- "13b-chat-q2_K",
- "5.4GB"
- ],
- [
- "13b-chat-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-chat-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-chat-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-chat-q4_0",
- "7.4GB"
- ],
- [
- "13b-chat-q4_1",
- "8.2GB"
- ],
- [
- "13b-chat-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-chat-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-chat-q5_0",
- "9.0GB"
- ],
- [
- "13b-chat-q5_1",
- "9.8GB"
- ],
- [
- "13b-chat-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-chat-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-chat-q6_K",
- "11GB"
- ],
- [
- "13b-chat-q8_0",
- "14GB"
- ],
- [
- "7b-chat",
- "3.8GB"
- ],
- [
- "7b-chat-fp16",
- "13GB"
- ],
- [
- "7b-chat-q2_K",
- "2.8GB"
- ],
- [
- "7b-chat-q3_K_L",
- "3.6GB"
- ],
- [
- "7b-chat-q3_K_M",
- "3.3GB"
- ],
- [
- "7b-chat-q3_K_S",
- "2.9GB"
- ],
- [
- "7b-chat-q4_0",
- "3.8GB"
- ],
- [
- "7b-chat-q4_1",
- "4.2GB"
- ],
- [
- "7b-chat-q4_K_M",
- "4.1GB"
- ],
- [
- "7b-chat-q4_K_S",
- "3.9GB"
- ],
- [
- "7b-chat-q5_0",
- "4.7GB"
- ],
- [
- "7b-chat-q5_1",
- "5.1GB"
- ],
- [
- "7b-chat-q5_K_M",
- "4.8GB"
- ],
- [
- "7b-chat-q5_K_S",
- "4.7GB"
- ],
- [
- "7b-chat-q6_K",
- "5.5GB"
- ],
- [
- "7b-chat-q8_0",
- "7.2GB"
- ]
- ],
- "image": false,
- "author": "Meta"
- },
"zephyr": {
"url": "https://ollama.com/library/zephyr",
"description": "Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.",
@@ -9060,7 +9044,35 @@
"19GB"
],
[
- "34b-chat-v1.5-q4_1",
+ "34b-chat-q5_K_S",
+ "24GB"
+ ],
+ [
+ "34b-chat-v1.5-q8_0",
+ "37GB"
+ ],
+ [
+ "34b-chat-v1.5-q5_K_M",
+ "24GB"
+ ],
+ [
+ "34b-chat-q4_K_M",
+ "21GB"
+ ],
+ [
+ "34b-chat-q5_0",
+ "24GB"
+ ],
+ [
+ "34b-chat-q2_K",
+ "15GB"
+ ],
+ [
+ "34b-chat-q3_K_L",
+ "18GB"
+ ],
+ [
+ "34b-chat-q4_1",
"22GB"
],
[
@@ -9068,71 +9080,15 @@
"21GB"
],
[
- "34b-chat-v1.5-q4_K_S",
- "20GB"
- ],
- [
- "34b-chat-v1.5-q5_0",
- "24GB"
- ],
- [
- "34b-chat-v1.5-q5_1",
- "26GB"
- ],
- [
- "34b-chat-v1.5-q5_K_M",
- "24GB"
+ "34b-chat-fp16",
+ "69GB"
],
[
"34b-chat-v1.5-q5_K_S",
"24GB"
],
[
- "34b-chat-q4_K_S",
- "20GB"
- ],
- [
- "34b-chat-q4_1",
- "22GB"
- ],
- [
- "34b-chat-fp16",
- "69GB"
- ],
- [
- "34b-chat-q3_K_M",
- "17GB"
- ],
- [
- "34b-chat-q3_K_L",
- "18GB"
- ],
- [
- "34b-chat-q4_0",
- "19GB"
- ],
- [
- "34b-chat-q3_K_S",
- "15GB"
- ],
- [
- "34b-chat-q4_K_M",
- "21GB"
- ],
- [
- "34b-chat-v1.5-q6_K",
- "28GB"
- ],
- [
- "34b-chat-v1.5-q8_0",
- "37GB"
- ],
- [
- "34b-chat-q2_K",
- "15GB"
- ],
- [
- "34b-chat-q5_0",
+ "34b-chat-v1.5-q5_0",
"24GB"
],
[
@@ -9144,8 +9100,36 @@
"24GB"
],
[
- "34b-chat-q5_K_S",
- "24GB"
+ "34b-chat-q3_K_M",
+ "17GB"
+ ],
+ [
+ "34b-chat-q4_K_S",
+ "20GB"
+ ],
+ [
+ "34b-chat-v1.5-q4_1",
+ "22GB"
+ ],
+ [
+ "34b-chat-q3_K_S",
+ "15GB"
+ ],
+ [
+ "34b-chat-v1.5-q5_1",
+ "26GB"
+ ],
+ [
+ "34b-chat-q4_0",
+ "19GB"
+ ],
+ [
+ "34b-chat-v1.5-q4_K_S",
+ "20GB"
+ ],
+ [
+ "34b-chat-v1.5-q6_K",
+ "28GB"
],
[
"34b-chat-q6_K",
@@ -9223,62 +9207,6 @@
"9b-chat",
"5.0GB"
],
- [
- "9b-v1.5",
- "5.0GB"
- ],
- [
- "6b-200k",
- "3.5GB"
- ],
- [
- "34b-q2_K",
- "15GB"
- ],
- [
- "34b-q3_K_L",
- "18GB"
- ],
- [
- "34b-q3_K_M",
- "17GB"
- ],
- [
- "34b-q3_K_S",
- "15GB"
- ],
- [
- "34b-q4_0",
- "19GB"
- ],
- [
- "34b-q4_1",
- "22GB"
- ],
- [
- "34b-q4_K_M",
- "21GB"
- ],
- [
- "34b-q4_K_S",
- "20GB"
- ],
- [
- "34b-q5_0",
- "24GB"
- ],
- [
- "34b-q5_1",
- "26GB"
- ],
- [
- "34b-q5_K_S",
- "24GB"
- ],
- [
- "34b-q6_K",
- "28GB"
- ],
[
"9b-chat-v1.5-fp16",
"18GB"
@@ -9339,6 +9267,10 @@
"9b-chat-v1.5-q8_0",
"9.4GB"
],
+ [
+ "9b-v1.5",
+ "5.0GB"
+ ],
[
"9b-v1.5-fp16",
"18GB"
@@ -9399,6 +9331,58 @@
"9b-v1.5-q8_0",
"9.4GB"
],
+ [
+ "6b-200k",
+ "3.5GB"
+ ],
+ [
+ "34b-q2_K",
+ "15GB"
+ ],
+ [
+ "34b-q3_K_L",
+ "18GB"
+ ],
+ [
+ "34b-q3_K_M",
+ "17GB"
+ ],
+ [
+ "34b-q3_K_S",
+ "15GB"
+ ],
+ [
+ "34b-q4_0",
+ "19GB"
+ ],
+ [
+ "34b-q4_1",
+ "22GB"
+ ],
+ [
+ "34b-q4_K_M",
+ "21GB"
+ ],
+ [
+ "34b-q4_K_S",
+ "20GB"
+ ],
+ [
+ "34b-q5_0",
+ "24GB"
+ ],
+ [
+ "34b-q5_1",
+ "26GB"
+ ],
+ [
+ "34b-q5_K_S",
+ "24GB"
+ ],
+ [
+ "34b-q6_K",
+ "28GB"
+ ],
[
"6b-200k-fp16",
"12GB"
@@ -9463,6 +9447,66 @@
"6b-chat",
"3.5GB"
],
+ [
+ "6b-chat-v1.5-fp16",
+ "12GB"
+ ],
+ [
+ "6b-chat-v1.5-q2_K",
+ "2.3GB"
+ ],
+ [
+ "6b-chat-v1.5-q3_K_L",
+ "3.2GB"
+ ],
+ [
+ "6b-chat-v1.5-q3_K_M",
+ "3.0GB"
+ ],
+ [
+ "6b-chat-v1.5-q3_K_S",
+ "2.7GB"
+ ],
+ [
+ "6b-chat-v1.5-q4_0",
+ "3.5GB"
+ ],
+ [
+ "6b-chat-v1.5-q4_1",
+ "3.8GB"
+ ],
+ [
+ "6b-chat-v1.5-q4_K_M",
+ "3.7GB"
+ ],
+ [
+ "6b-chat-q4_0",
+ "3.5GB"
+ ],
+ [
+ "6b-chat-v1.5-q8_0",
+ "6.4GB"
+ ],
+ [
+ "6b-chat-q3_K_L",
+ "3.2GB"
+ ],
+ [
+ "6b-chat-v1.5-q5_K_S",
+ "4.2GB"
+ ],
+ [
+ "6b-chat-v1.5-q4_K_S",
+ "3.5GB"
+ ],
+ [
+ "6b-chat-v1.5-q5_K_M",
+ "4.3GB"
+ ],
+ [
+ "6b-chat-v1.5-q5_1",
+ "4.6GB"
+ ],
[
"6b-chat-fp16",
"12GB"
@@ -9471,33 +9515,33 @@
"6b-chat-q2_K",
"2.6GB"
],
- [
- "6b-chat-q3_K_L",
- "3.2GB"
- ],
[
"6b-chat-q3_K_M",
"3.0GB"
],
+ [
+ "6b-chat-v1.5-q6_K",
+ "5.0GB"
+ ],
[
"6b-chat-q3_K_S",
"2.7GB"
],
[
- "6b-chat-q4_0",
- "3.5GB"
+ "6b-chat-v1.5-q5_0",
+ "4.2GB"
],
[
- "6b-chat-q4_1",
- "3.8GB"
+ "6b-chat-q4_K_S",
+ "3.5GB"
],
[
"6b-chat-q4_K_M",
"3.7GB"
],
[
- "6b-chat-q4_K_S",
- "3.5GB"
+ "6b-chat-q4_1",
+ "3.8GB"
],
[
"6b-chat-q5_0",
@@ -9508,79 +9552,19 @@
"4.6GB"
],
[
- "6b-chat-v1.5-q4_K_M",
- "3.7GB"
+ "6b-chat-q5_K_M",
+ "4.3GB"
],
[
"6b-chat-q5_K_S",
"4.2GB"
],
- [
- "6b-chat-q5_K_M",
- "4.3GB"
- ],
- [
- "6b-chat-v1.5-fp16",
- "12GB"
- ],
- [
- "6b-chat-v1.5-q4_1",
- "3.8GB"
- ],
- [
- "6b-chat-v1.5-q2_K",
- "2.3GB"
- ],
- [
- "6b-chat-v1.5-q3_K_S",
- "2.7GB"
- ],
- [
- "6b-chat-q8_0",
- "6.4GB"
- ],
- [
- "6b-chat-v1.5-q4_0",
- "3.5GB"
- ],
- [
- "6b-chat-v1.5-q3_K_M",
- "3.0GB"
- ],
- [
- "6b-chat-v1.5-q3_K_L",
- "3.2GB"
- ],
[
"6b-chat-q6_K",
"5.0GB"
],
[
- "6b-chat-v1.5-q4_K_S",
- "3.5GB"
- ],
- [
- "6b-chat-v1.5-q5_0",
- "4.2GB"
- ],
- [
- "6b-chat-v1.5-q5_1",
- "4.6GB"
- ],
- [
- "6b-chat-v1.5-q5_K_M",
- "4.3GB"
- ],
- [
- "6b-chat-v1.5-q5_K_S",
- "4.2GB"
- ],
- [
- "6b-chat-v1.5-q6_K",
- "5.0GB"
- ],
- [
- "6b-chat-v1.5-q8_0",
+ "6b-chat-q8_0",
"6.4GB"
],
[
@@ -9711,6 +9695,630 @@
"image": false,
"author": "01.AI"
},
+ "llama2-chinese": {
+ "url": "https://ollama.com/library/llama2-chinese",
+ "description": "Llama 2 based model fine tuned to improve Chinese dialogue ability.",
+ "tags": [
+ [
+ "latest",
+ "3.8GB"
+ ],
+ [
+ "13b",
+ "7.4GB"
+ ],
+ [
+ "7b",
+ "3.8GB"
+ ],
+ [
+ "13b-chat",
+ "7.4GB"
+ ],
+ [
+ "13b-chat-fp16",
+ "26GB"
+ ],
+ [
+ "13b-chat-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-chat-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-chat-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-chat-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-chat-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-chat-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-chat-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-chat-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-chat-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-chat-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-chat-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-chat-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-chat-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-chat-q8_0",
+ "14GB"
+ ],
+ [
+ "7b-chat",
+ "3.8GB"
+ ],
+ [
+ "7b-chat-fp16",
+ "13GB"
+ ],
+ [
+ "7b-chat-q2_K",
+ "2.8GB"
+ ],
+ [
+ "7b-chat-q3_K_L",
+ "3.6GB"
+ ],
+ [
+ "7b-chat-q3_K_M",
+ "3.3GB"
+ ],
+ [
+ "7b-chat-q3_K_S",
+ "2.9GB"
+ ],
+ [
+ "7b-chat-q4_0",
+ "3.8GB"
+ ],
+ [
+ "7b-chat-q4_1",
+ "4.2GB"
+ ],
+ [
+ "7b-chat-q4_K_M",
+ "4.1GB"
+ ],
+ [
+ "7b-chat-q4_K_S",
+ "3.9GB"
+ ],
+ [
+ "7b-chat-q5_0",
+ "4.7GB"
+ ],
+ [
+ "7b-chat-q5_1",
+ "5.1GB"
+ ],
+ [
+ "7b-chat-q5_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-chat-q5_K_S",
+ "4.7GB"
+ ],
+ [
+ "7b-chat-q6_K",
+ "5.5GB"
+ ],
+ [
+ "7b-chat-q8_0",
+ "7.2GB"
+ ]
+ ],
+ "image": false,
+ "author": "Meta"
+ },
+ "llava-llama3": {
+ "url": "https://ollama.com/library/llava-llama3",
+ "description": "A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.",
+ "tags": [
+ [
+ "latest",
+ "5.5GB"
+ ],
+ [
+ "8b",
+ "5.5GB"
+ ],
+ [
+ "8b-v1.1-fp16",
+ "17GB"
+ ],
+ [
+ "8b-v1.1-q4_0",
+ "5.5GB"
+ ]
+ ],
+ "image": true,
+ "author": "Xtuner"
+ },
+ "vicuna": {
+ "url": "https://ollama.com/library/vicuna",
+ "description": "General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.",
+ "tags": [
+ [
+ "latest",
+ "3.8GB"
+ ],
+ [
+ "33b",
+ "18GB"
+ ],
+ [
+ "13b",
+ "7.4GB"
+ ],
+ [
+ "7b",
+ "3.8GB"
+ ],
+ [
+ "13b-16k",
+ "7.4GB"
+ ],
+ [
+ "33b-fp16",
+ "65GB"
+ ],
+ [
+ "33b-q2_K",
+ "14GB"
+ ],
+ [
+ "33b-q3_K_L",
+ "17GB"
+ ],
+ [
+ "33b-q3_K_M",
+ "16GB"
+ ],
+ [
+ "33b-q3_K_S",
+ "14GB"
+ ],
+ [
+ "33b-q4_0",
+ "18GB"
+ ],
+ [
+ "33b-q4_1",
+ "20GB"
+ ],
+ [
+ "33b-q4_K_M",
+ "20GB"
+ ],
+ [
+ "33b-q4_K_S",
+ "18GB"
+ ],
+ [
+ "33b-q5_0",
+ "22GB"
+ ],
+ [
+ "33b-q5_1",
+ "24GB"
+ ],
+ [
+ "33b-q5_K_M",
+ "23GB"
+ ],
+ [
+ "33b-q5_K_S",
+ "22GB"
+ ],
+ [
+ "33b-q6_K",
+ "27GB"
+ ],
+ [
+ "33b-q8_0",
+ "35GB"
+ ],
+ [
+ "13b-v1.5-16k-fp16",
+ "26GB"
+ ],
+ [
+ "13b-v1.5-16k-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-v1.5-16k-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-v1.5-16k-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-v1.5-16k-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-v1.5-16k-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-v1.5-16k-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-v1.5-16k-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-v1.5-16k-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-v1.5-16k-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-v1.5-16k-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-v1.5-16k-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-v1.5-16k-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-v1.5-16k-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-v1.5-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-v1.5-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-v1.5-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-v1.5-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-v1.5-16k-q8_0",
+ "14GB"
+ ],
+ [
+ "13b-v1.5-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-v1.5-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-v1.5-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-v1.5-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-v1.5-fp16",
+ "26GB"
+ ],
+ [
+ "13b-v1.5-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-v1.5-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-v1.5-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-v1.5-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-v1.5-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-v1.5-q8_0",
+ "14GB"
+ ],
+ [
+ "7b-16k",
+ "3.8GB"
+ ],
+ [
+ "13b-fp16",
+ "26GB"
+ ],
+ [
+ "13b-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-q8_0",
+ "14GB"
+ ],
+ [
+ "7b-v1.5-fp16",
+ "13GB"
+ ],
+ [
+ "7b-v1.5-q2_K",
+ "2.8GB"
+ ],
+ [
+ "7b-v1.5-q3_K_L",
+ "3.6GB"
+ ],
+ [
+ "7b-v1.5-q3_K_M",
+ "3.3GB"
+ ],
+ [
+ "7b-v1.5-q3_K_S",
+ "2.9GB"
+ ],
+ [
+ "7b-v1.5-q4_0",
+ "3.8GB"
+ ],
+ [
+ "7b-v1.5-q4_1",
+ "4.2GB"
+ ],
+ [
+ "7b-v1.5-q4_K_M",
+ "4.1GB"
+ ],
+ [
+ "7b-v1.5-q4_K_S",
+ "3.9GB"
+ ],
+ [
+ "7b-v1.5-q5_0",
+ "4.7GB"
+ ],
+ [
+ "7b-v1.5-16k-q8_0",
+ "7.2GB"
+ ],
+ [
+ "7b-v1.5-q5_1",
+ "5.1GB"
+ ],
+ [
+ "7b-v1.5-16k-q3_K_L",
+ "3.6GB"
+ ],
+ [
+ "7b-v1.5-q6_K",
+ "5.5GB"
+ ],
+ [
+ "7b-v1.5-16k-q3_K_S",
+ "2.9GB"
+ ],
+ [
+ "7b-v1.5-16k-q4_1",
+ "4.2GB"
+ ],
+ [
+ "7b-v1.5-q8_0",
+ "7.2GB"
+ ],
+ [
+ "7b-v1.5-16k-q5_K_S",
+ "4.7GB"
+ ],
+ [
+ "7b-v1.5-16k-q2_K",
+ "2.8GB"
+ ],
+ [
+ "7b-v1.5-q5_K_S",
+ "4.7GB"
+ ],
+ [
+ "7b-v1.5-16k-q3_K_M",
+ "3.3GB"
+ ],
+ [
+ "7b-v1.5-16k-q5_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-v1.5-16k-q6_K",
+ "5.5GB"
+ ],
+ [
+ "7b-v1.5-16k-q4_K_M",
+ "4.1GB"
+ ],
+ [
+ "7b-v1.5-16k-q4_K_S",
+ "3.9GB"
+ ],
+ [
+ "7b-v1.5-q5_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-v1.5-16k-fp16",
+ "13GB"
+ ],
+ [
+ "7b-v1.5-16k-q4_0",
+ "3.8GB"
+ ],
+ [
+ "7b-v1.5-16k-q5_0",
+ "4.7GB"
+ ],
+ [
+ "7b-v1.5-16k-q5_1",
+ "5.1GB"
+ ],
+ [
+ "7b-fp16",
+ "13GB"
+ ],
+ [
+ "7b-q2_K",
+ "2.8GB"
+ ],
+ [
+ "7b-q3_K_L",
+ "3.6GB"
+ ],
+ [
+ "7b-q3_K_M",
+ "3.3GB"
+ ],
+ [
+ "7b-q3_K_S",
+ "2.9GB"
+ ],
+ [
+ "7b-q4_0",
+ "3.8GB"
+ ],
+ [
+ "7b-q4_1",
+ "4.2GB"
+ ],
+ [
+ "7b-q4_K_M",
+ "4.1GB"
+ ],
+ [
+ "7b-q4_K_S",
+ "3.9GB"
+ ],
+ [
+ "7b-q5_0",
+ "4.7GB"
+ ],
+ [
+ "7b-q5_1",
+ "5.1GB"
+ ],
+ [
+ "7b-q5_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-q5_K_S",
+ "4.7GB"
+ ],
+ [
+ "7b-q6_K",
+ "5.5GB"
+ ],
+ [
+ "7b-q8_0",
+ "7.2GB"
+ ]
+ ],
+ "image": false,
+ "author": "lmsys.org"
+ },
"nous-hermes2": {
"url": "https://ollama.com/library/nous-hermes2",
"description": "The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.",
@@ -9851,458 +10459,6 @@
"image": false,
"author": "Nous Research"
},
- "vicuna": {
- "url": "https://ollama.com/library/vicuna",
- "description": "General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.",
- "tags": [
- [
- "latest",
- "3.8GB"
- ],
- [
- "33b",
- "18GB"
- ],
- [
- "13b",
- "7.4GB"
- ],
- [
- "7b",
- "3.8GB"
- ],
- [
- "13b-16k",
- "7.4GB"
- ],
- [
- "33b-fp16",
- "65GB"
- ],
- [
- "33b-q2_K",
- "14GB"
- ],
- [
- "33b-q3_K_L",
- "17GB"
- ],
- [
- "33b-q3_K_M",
- "16GB"
- ],
- [
- "33b-q3_K_S",
- "14GB"
- ],
- [
- "33b-q4_0",
- "18GB"
- ],
- [
- "33b-q4_1",
- "20GB"
- ],
- [
- "33b-q4_K_M",
- "20GB"
- ],
- [
- "33b-q4_K_S",
- "18GB"
- ],
- [
- "33b-q5_0",
- "22GB"
- ],
- [
- "33b-q5_1",
- "24GB"
- ],
- [
- "33b-q5_K_M",
- "23GB"
- ],
- [
- "33b-q5_K_S",
- "22GB"
- ],
- [
- "33b-q6_K",
- "27GB"
- ],
- [
- "33b-q8_0",
- "35GB"
- ],
- [
- "13b-v1.5-16k-fp16",
- "26GB"
- ],
- [
- "13b-v1.5-16k-q2_K",
- "5.4GB"
- ],
- [
- "13b-v1.5-16k-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-v1.5-16k-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-v1.5-16k-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-v1.5-16k-q4_0",
- "7.4GB"
- ],
- [
- "13b-v1.5-16k-q4_1",
- "8.2GB"
- ],
- [
- "13b-v1.5-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-v1.5-16k-q5_1",
- "9.8GB"
- ],
- [
- "13b-v1.5-16k-q5_0",
- "9.0GB"
- ],
- [
- "13b-v1.5-16k-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-v1.5-16k-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-v1.5-16k-q6_K",
- "11GB"
- ],
- [
- "13b-v1.5-16k-q8_0",
- "14GB"
- ],
- [
- "13b-v1.5-16k-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-v1.5-fp16",
- "26GB"
- ],
- [
- "13b-v1.5-16k-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-v1.5-q2_K",
- "5.4GB"
- ],
- [
- "13b-v1.5-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-v1.5-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-v1.5-q4_0",
- "7.4GB"
- ],
- [
- "13b-v1.5-q4_1",
- "8.2GB"
- ],
- [
- "13b-v1.5-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-v1.5-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-v1.5-q5_0",
- "9.0GB"
- ],
- [
- "13b-v1.5-q5_1",
- "9.8GB"
- ],
- [
- "13b-v1.5-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-v1.5-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-v1.5-q6_K",
- "11GB"
- ],
- [
- "13b-v1.5-q8_0",
- "14GB"
- ],
- [
- "7b-16k",
- "3.8GB"
- ],
- [
- "13b-fp16",
- "26GB"
- ],
- [
- "13b-q2_K",
- "5.4GB"
- ],
- [
- "13b-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-q4_0",
- "7.4GB"
- ],
- [
- "13b-q4_1",
- "8.2GB"
- ],
- [
- "13b-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-q5_0",
- "9.0GB"
- ],
- [
- "13b-q5_1",
- "9.8GB"
- ],
- [
- "13b-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-q6_K",
- "11GB"
- ],
- [
- "13b-q8_0",
- "14GB"
- ],
- [
- "7b-v1.5-16k-fp16",
- "13GB"
- ],
- [
- "7b-v1.5-16k-q2_K",
- "2.8GB"
- ],
- [
- "7b-v1.5-16k-q3_K_L",
- "3.6GB"
- ],
- [
- "7b-v1.5-16k-q3_K_M",
- "3.3GB"
- ],
- [
- "7b-v1.5-16k-q3_K_S",
- "2.9GB"
- ],
- [
- "7b-v1.5-16k-q4_0",
- "3.8GB"
- ],
- [
- "7b-v1.5-16k-q4_1",
- "4.2GB"
- ],
- [
- "7b-v1.5-16k-q4_K_M",
- "4.1GB"
- ],
- [
- "7b-v1.5-16k-q4_K_S",
- "3.9GB"
- ],
- [
- "7b-v1.5-16k-q5_0",
- "4.7GB"
- ],
- [
- "7b-v1.5-16k-q5_1",
- "5.1GB"
- ],
- [
- "7b-v1.5-16k-q5_K_M",
- "4.8GB"
- ],
- [
- "7b-v1.5-16k-q5_K_S",
- "4.7GB"
- ],
- [
- "7b-v1.5-16k-q6_K",
- "5.5GB"
- ],
- [
- "7b-v1.5-16k-q8_0",
- "7.2GB"
- ],
- [
- "7b-v1.5-q4_0",
- "3.8GB"
- ],
- [
- "7b-v1.5-q3_K_L",
- "3.6GB"
- ],
- [
- "7b-v1.5-fp16",
- "13GB"
- ],
- [
- "7b-v1.5-q3_K_S",
- "2.9GB"
- ],
- [
- "7b-v1.5-q2_K",
- "2.8GB"
- ],
- [
- "7b-v1.5-q3_K_M",
- "3.3GB"
- ],
- [
- "7b-v1.5-q4_1",
- "4.2GB"
- ],
- [
- "7b-v1.5-q4_K_M",
- "4.1GB"
- ],
- [
- "7b-v1.5-q4_K_S",
- "3.9GB"
- ],
- [
- "7b-v1.5-q5_0",
- "4.7GB"
- ],
- [
- "7b-v1.5-q5_1",
- "5.1GB"
- ],
- [
- "7b-v1.5-q5_K_M",
- "4.8GB"
- ],
- [
- "7b-v1.5-q5_K_S",
- "4.7GB"
- ],
- [
- "7b-v1.5-q6_K",
- "5.5GB"
- ],
- [
- "7b-v1.5-q8_0",
- "7.2GB"
- ],
- [
- "7b-fp16",
- "13GB"
- ],
- [
- "7b-q2_K",
- "2.8GB"
- ],
- [
- "7b-q3_K_L",
- "3.6GB"
- ],
- [
- "7b-q3_K_M",
- "3.3GB"
- ],
- [
- "7b-q3_K_S",
- "2.9GB"
- ],
- [
- "7b-q4_0",
- "3.8GB"
- ],
- [
- "7b-q4_1",
- "4.2GB"
- ],
- [
- "7b-q4_K_M",
- "4.1GB"
- ],
- [
- "7b-q4_K_S",
- "3.9GB"
- ],
- [
- "7b-q5_0",
- "4.7GB"
- ],
- [
- "7b-q5_1",
- "5.1GB"
- ],
- [
- "7b-q5_K_M",
- "4.8GB"
- ],
- [
- "7b-q5_K_S",
- "4.7GB"
- ],
- [
- "7b-q6_K",
- "5.5GB"
- ],
- [
- "7b-q8_0",
- "7.2GB"
- ]
- ],
- "image": false,
- "author": "lmsys.org"
- },
"wizard-vicuna-uncensored": {
"url": "https://ollama.com/library/wizard-vicuna-uncensored",
"description": "Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.",
@@ -10659,101 +10815,85 @@
"image": false,
"author": "TinyLlama Team"
},
- "wizardlm2": {
- "url": "https://ollama.com/library/wizardlm2",
- "description": "State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.",
+ "codestral": {
+ "url": "https://ollama.com/library/codestral",
+ "description": "Codestral is Mistral AI\u2019s first-ever code model designed for code generation tasks.",
"tags": [
[
"latest",
- "4.1GB"
+ "13GB"
],
[
- "8x22b",
- "80GB"
+ "22b",
+ "13GB"
],
[
- "7b",
- "4.1GB"
+ "v0.1",
+ "13GB"
],
[
- "8x22b-fp16",
- "281GB"
+ "22b-v0.1-f16",
+ "44GB"
],
[
- "8x22b-q2_K",
- "52GB"
+ "22b-v0.1-q2_K",
+ "8.3GB"
],
[
- "8x22b-q4_0",
- "80GB"
+ "22b-v0.1-q3_K_L",
+ "12GB"
],
[
- "8x22b-q8_0",
- "149GB"
+ "22b-v0.1-q3_K_M",
+ "11GB"
],
[
- "7b-fp16",
+ "22b-v0.1-q3_K_S",
+ "9.6GB"
+ ],
+ [
+ "22b-v0.1-q4_0",
+ "13GB"
+ ],
+ [
+ "22b-v0.1-q4_1",
"14GB"
],
[
- "7b-q2_K",
- "2.7GB"
+ "22b-v0.1-q4_K_M",
+ "13GB"
],
[
- "7b-q3_K_L",
- "3.8GB"
+ "22b-v0.1-q4_K_S",
+ "13GB"
],
[
- "7b-q3_K_M",
- "3.5GB"
+ "22b-v0.1-q5_0",
+ "15GB"
],
[
- "7b-q3_K_S",
- "3.2GB"
+ "22b-v0.1-q5_1",
+ "17GB"
],
[
- "7b-q4_0",
- "4.1GB"
+ "22b-v0.1-q5_K_M",
+ "16GB"
],
[
- "7b-q4_1",
- "4.6GB"
+ "22b-v0.1-q5_K_S",
+ "15GB"
],
[
- "7b-q4_K_M",
- "4.4GB"
+ "22b-v0.1-q6_K",
+ "18GB"
],
[
- "7b-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-q5_0",
- "5.0GB"
- ],
- [
- "7b-q5_1",
- "5.4GB"
- ],
- [
- "7b-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-q6_K",
- "5.9GB"
- ],
- [
- "7b-q8_0",
- "7.7GB"
+ "22b-v0.1-q8_0",
+ "24GB"
]
],
"image": false,
- "author": "Microsoft"
+ "author": "Mistral AI"
},
"starcoder": {
"url": "https://ollama.com/library/starcoder",
@@ -10911,6 +11051,10 @@
"7b-base",
"4.3GB"
],
+ [
+ "3b-base",
+ "1.8GB"
+ ],
[
"15b-fp16",
"32GB"
@@ -11031,10 +11175,6 @@
"7b-base-q8_0",
"8.0GB"
],
- [
- "3b-base",
- "1.8GB"
- ],
[
"3b-base-fp16",
"6.4GB"
@@ -11163,85 +11303,101 @@
"image": false,
"author": "BigCode"
},
- "codestral": {
- "url": "https://ollama.com/library/codestral",
- "description": "Codestral is Mistral AI\u2019s first-ever code model designed for code generation tasks.",
+ "wizardlm2": {
+ "url": "https://ollama.com/library/wizardlm2",
+ "description": "State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.",
"tags": [
[
"latest",
- "13GB"
+ "4.1GB"
],
[
- "22b",
- "13GB"
+ "8x22b",
+ "80GB"
],
[
- "v0.1",
- "13GB"
+ "7b",
+ "4.1GB"
],
[
- "22b-v0.1-f16",
- "44GB"
+ "8x22b-fp16",
+ "281GB"
],
[
- "22b-v0.1-q2_K",
- "8.3GB"
+ "8x22b-q2_K",
+ "52GB"
],
[
- "22b-v0.1-q3_K_L",
- "12GB"
+ "8x22b-q4_0",
+ "80GB"
],
[
- "22b-v0.1-q3_K_M",
- "11GB"
+ "8x22b-q8_0",
+ "149GB"
],
[
- "22b-v0.1-q3_K_S",
- "9.6GB"
- ],
- [
- "22b-v0.1-q4_0",
- "13GB"
- ],
- [
- "22b-v0.1-q4_1",
+ "7b-fp16",
"14GB"
],
[
- "22b-v0.1-q4_K_M",
- "13GB"
+ "7b-q2_K",
+ "2.7GB"
],
[
- "22b-v0.1-q4_K_S",
- "13GB"
+ "7b-q3_K_L",
+ "3.8GB"
],
[
- "22b-v0.1-q5_0",
- "15GB"
+ "7b-q3_K_M",
+ "3.5GB"
],
[
- "22b-v0.1-q5_1",
- "17GB"
+ "7b-q3_K_S",
+ "3.2GB"
],
[
- "22b-v0.1-q5_K_M",
- "16GB"
+ "7b-q4_0",
+ "4.1GB"
],
[
- "22b-v0.1-q5_K_S",
- "15GB"
+ "7b-q4_1",
+ "4.6GB"
],
[
- "22b-v0.1-q6_K",
- "18GB"
+ "7b-q4_K_M",
+ "4.4GB"
],
[
- "22b-v0.1-q8_0",
- "24GB"
+ "7b-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-q8_0",
+ "7.7GB"
]
],
"image": false,
- "author": "Mistral AI"
+ "author": "Microsoft"
},
"openchat": {
"url": "https://ollama.com/library/openchat",
@@ -11256,11 +11412,11 @@
"4.1GB"
],
[
- "7b-v3.5-0106",
+ "7b-v3.5",
"4.1GB"
],
[
- "7b-v3.5",
+ "7b-v3.5-0106",
"4.1GB"
],
[
@@ -11327,89 +11483,13 @@
"7b-v3.5-0106-q8_0",
"7.7GB"
],
- [
- "7b-v3.5-q6_K",
- "5.9GB"
- ],
- [
- "7b-v3.5-1210-q2_K",
- "3.1GB"
- ],
- [
- "7b-v3.5-fp16",
- "14GB"
- ],
- [
- "7b-v3.5-q4_K_M",
- "4.4GB"
- ],
- [
- "7b-v3.5-q2_K",
- "3.1GB"
- ],
- [
- "7b-v3.5-1210-q6_K",
- "5.9GB"
- ],
- [
- "7b-v3.5-1210-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-v3.5-q3_K_L",
- "3.8GB"
- ],
- [
- "7b-v3.5-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-v3.5-1210-q5_0",
- "5.0GB"
- ],
- [
- "7b-v3.5-1210-q4_0",
- "4.1GB"
- ],
[
"7b-v3.5-1210-fp16",
"14GB"
],
[
- "7b-v3.5-1210-q4_1",
- "4.6GB"
- ],
- [
- "7b-v3.5-1210-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-v3.5-1210-q4_K_M",
- "4.4GB"
- ],
- [
- "7b-v3.5-1210-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-v3.5-1210-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-v3.5-1210-q8_0",
- "7.7GB"
- ],
- [
- "7b-v3.5-1210-q5_1",
- "5.4GB"
- ],
- [
- "7b-v3.5-q4_0",
- "4.1GB"
- ],
- [
- "7b-v3.5-q5_1",
- "5.4GB"
+ "7b-v3.5-1210-q2_K",
+ "3.1GB"
],
[
"7b-v3.5-1210-q3_K_L",
@@ -11419,10 +11499,94 @@
"7b-v3.5-1210-q3_K_M",
"3.5GB"
],
+ [
+ "7b-v3.5-1210-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-v3.5-1210-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-v3.5-1210-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-v3.5-1210-q4_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-v3.5-1210-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-v3.5-1210-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-v3.5-1210-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-v3.5-1210-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-v3.5-1210-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-v3.5-1210-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-v3.5-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-v3.5-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-v3.5-q2_K",
+ "3.1GB"
+ ],
+ [
+ "7b-v3.5-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-v3.5-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-v3.5-1210-q8_0",
+ "7.7GB"
+ ],
+ [
+ "7b-v3.5-fp16",
+ "14GB"
+ ],
+ [
+ "7b-v3.5-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-v3.5-q4_K_M",
+ "4.4GB"
+ ],
[
"7b-v3.5-q4_K_S",
"4.1GB"
],
+ [
+ "7b-v3.5-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-v3.5-q5_1",
+ "5.4GB"
+ ],
[
"7b-v3.5-q5_K_M",
"5.1GB"
@@ -11432,16 +11596,8 @@
"5.0GB"
],
[
- "7b-v3.5-q3_K_M",
- "3.5GB"
- ],
- [
- "7b-v3.5-q5_0",
- "5.0GB"
- ],
- [
- "7b-v3.5-q4_1",
- "4.6GB"
+ "7b-v3.5-q6_K",
+ "5.9GB"
],
[
"7b-v3.5-q8_0",
@@ -11540,11 +11696,11 @@
"4.1GB"
],
[
- "v2",
+ "v2.5",
"4.1GB"
],
[
- "v2.5",
+ "v2",
"4.1GB"
],
[
@@ -12107,6 +12263,134 @@
"image": false,
"author": "Stability AI"
},
+ "codeqwen": {
+ "url": "https://ollama.com/library/codeqwen",
+ "description": "CodeQwen1.5 is a large language model pretrained on a large amount of code data.",
+ "tags": [
+ [
+ "latest",
+ "4.2GB"
+ ],
+ [
+ "7b",
+ "4.2GB"
+ ],
+ [
+ "chat",
+ "4.2GB"
+ ],
+ [
+ "code",
+ "4.2GB"
+ ],
+ [
+ "v1.5",
+ "4.2GB"
+ ],
+ [
+ "7b-chat",
+ "4.2GB"
+ ],
+ [
+ "7b-chat-v1.5-fp16",
+ "15GB"
+ ],
+ [
+ "7b-chat-v1.5-q2_K",
+ "3.1GB"
+ ],
+ [
+ "7b-chat-v1.5-q3_K_L",
+ "4.0GB"
+ ],
+ [
+ "7b-chat-v1.5-q3_K_M",
+ "3.8GB"
+ ],
+ [
+ "7b-chat-v1.5-q3_K_S",
+ "3.5GB"
+ ],
+ [
+ "7b-chat-v1.5-q4_0",
+ "4.2GB"
+ ],
+ [
+ "7b-chat-v1.5-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-chat-v1.5-q4_K_M",
+ "4.7GB"
+ ],
+ [
+ "7b-chat-v1.5-q4_K_S",
+ "4.4GB"
+ ],
+ [
+ "7b-chat-v1.5-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-chat-v1.5-q5_1",
+ "5.5GB"
+ ],
+ [
+ "7b-chat-v1.5-q5_K_M",
+ "5.4GB"
+ ],
+ [
+ "7b-chat-v1.5-q5_K_S",
+ "5.1GB"
+ ],
+ [
+ "7b-chat-v1.5-q6_K",
+ "6.4GB"
+ ],
+ [
+ "7b-chat-v1.5-q8_0",
+ "7.7GB"
+ ],
+ [
+ "7b-code",
+ "4.2GB"
+ ],
+ [
+ "7b-code-v1.5-fp16",
+ "15GB"
+ ],
+ [
+ "7b-code-v1.5-q4_0",
+ "4.2GB"
+ ],
+ [
+ "7b-code-v1.5-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-code-v1.5-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-code-v1.5-q5_1",
+ "5.5GB"
+ ],
+ [
+ "7b-code-v1.5-q8_0",
+ "7.7GB"
+ ],
+ [
+ "v1.5-chat",
+ "4.2GB"
+ ],
+ [
+ "v1.5-code",
+ "4.2GB"
+ ]
+ ],
+ "image": false,
+ "author": "Alibaba"
+ },
"neural-chat": {
"url": "https://ollama.com/library/neural-chat",
"description": "A fine-tuned model based on Mistral with good coverage of domain and language.",
@@ -12579,338 +12863,6 @@
"image": false,
"author": "WizardLM Team"
},
- "codeqwen": {
- "url": "https://ollama.com/library/codeqwen",
- "description": "CodeQwen1.5 is a large language model pretrained on a large amount of code data.",
- "tags": [
- [
- "latest",
- "4.2GB"
- ],
- [
- "7b",
- "4.2GB"
- ],
- [
- "chat",
- "4.2GB"
- ],
- [
- "code",
- "4.2GB"
- ],
- [
- "v1.5",
- "4.2GB"
- ],
- [
- "7b-chat",
- "4.2GB"
- ],
- [
- "7b-chat-v1.5-fp16",
- "15GB"
- ],
- [
- "7b-chat-v1.5-q2_K",
- "3.1GB"
- ],
- [
- "7b-chat-v1.5-q3_K_L",
- "4.0GB"
- ],
- [
- "7b-chat-v1.5-q3_K_M",
- "3.8GB"
- ],
- [
- "7b-chat-v1.5-q3_K_S",
- "3.5GB"
- ],
- [
- "7b-chat-v1.5-q4_0",
- "4.2GB"
- ],
- [
- "7b-chat-v1.5-q4_1",
- "4.6GB"
- ],
- [
- "7b-chat-v1.5-q4_K_M",
- "4.7GB"
- ],
- [
- "7b-chat-v1.5-q4_K_S",
- "4.4GB"
- ],
- [
- "7b-chat-v1.5-q5_0",
- "5.0GB"
- ],
- [
- "7b-chat-v1.5-q5_1",
- "5.5GB"
- ],
- [
- "7b-chat-v1.5-q5_K_M",
- "5.4GB"
- ],
- [
- "7b-chat-v1.5-q5_K_S",
- "5.1GB"
- ],
- [
- "7b-chat-v1.5-q6_K",
- "6.4GB"
- ],
- [
- "7b-chat-v1.5-q8_0",
- "7.7GB"
- ],
- [
- "7b-code",
- "4.2GB"
- ],
- [
- "7b-code-v1.5-fp16",
- "15GB"
- ],
- [
- "7b-code-v1.5-q4_0",
- "4.2GB"
- ],
- [
- "7b-code-v1.5-q4_1",
- "4.6GB"
- ],
- [
- "7b-code-v1.5-q5_0",
- "5.0GB"
- ],
- [
- "7b-code-v1.5-q5_1",
- "5.5GB"
- ],
- [
- "7b-code-v1.5-q8_0",
- "7.7GB"
- ],
- [
- "v1.5-chat",
- "4.2GB"
- ],
- [
- "v1.5-code",
- "4.2GB"
- ]
- ],
- "image": false,
- "author": "Alibaba"
- },
- "phind-codellama": {
- "url": "https://ollama.com/library/phind-codellama",
- "description": "Code generation model based on Code Llama.",
- "tags": [
- [
- "latest",
- "19GB"
- ],
- [
- "34b",
- "19GB"
- ],
- [
- "34b-python",
- "19GB"
- ],
- [
- "34b-python-fp16",
- "67GB"
- ],
- [
- "34b-python-q2_K",
- "14GB"
- ],
- [
- "34b-python-q3_K_L",
- "18GB"
- ],
- [
- "34b-python-q3_K_M",
- "16GB"
- ],
- [
- "34b-python-q3_K_S",
- "15GB"
- ],
- [
- "34b-python-q4_0",
- "19GB"
- ],
- [
- "34b-python-q4_1",
- "21GB"
- ],
- [
- "34b-python-q4_K_M",
- "20GB"
- ],
- [
- "34b-python-q4_K_S",
- "19GB"
- ],
- [
- "34b-python-q5_0",
- "23GB"
- ],
- [
- "34b-python-q5_1",
- "25GB"
- ],
- [
- "34b-python-q5_K_M",
- "24GB"
- ],
- [
- "34b-python-q5_K_S",
- "23GB"
- ],
- [
- "34b-python-q6_K",
- "28GB"
- ],
- [
- "34b-python-q8_0",
- "36GB"
- ],
- [
- "34b-v2",
- "19GB"
- ],
- [
- "34b-v2-fp16",
- "67GB"
- ],
- [
- "34b-v2-q2_K",
- "14GB"
- ],
- [
- "34b-v2-q3_K_L",
- "18GB"
- ],
- [
- "34b-v2-q3_K_M",
- "16GB"
- ],
- [
- "34b-v2-q3_K_S",
- "15GB"
- ],
- [
- "34b-v2-q4_0",
- "19GB"
- ],
- [
- "34b-v2-q4_1",
- "21GB"
- ],
- [
- "34b-v2-q4_K_M",
- "20GB"
- ],
- [
- "34b-v2-q4_K_S",
- "19GB"
- ],
- [
- "34b-v2-q5_0",
- "23GB"
- ],
- [
- "34b-v2-q5_1",
- "25GB"
- ],
- [
- "34b-v2-q5_K_M",
- "24GB"
- ],
- [
- "34b-v2-q5_K_S",
- "23GB"
- ],
- [
- "34b-v2-q6_K",
- "28GB"
- ],
- [
- "34b-v2-q8_0",
- "36GB"
- ],
- [
- "34b-fp16",
- "67GB"
- ],
- [
- "34b-q2_K",
- "14GB"
- ],
- [
- "34b-q3_K_L",
- "18GB"
- ],
- [
- "34b-q3_K_M",
- "16GB"
- ],
- [
- "34b-q3_K_S",
- "15GB"
- ],
- [
- "34b-q4_0",
- "19GB"
- ],
- [
- "34b-q4_1",
- "21GB"
- ],
- [
- "34b-q4_K_M",
- "20GB"
- ],
- [
- "34b-q4_K_S",
- "19GB"
- ],
- [
- "34b-q5_0",
- "23GB"
- ],
- [
- "34b-q5_1",
- "25GB"
- ],
- [
- "34b-q5_K_M",
- "24GB"
- ],
- [
- "34b-q5_K_S",
- "23GB"
- ],
- [
- "34b-q6_K",
- "28GB"
- ],
- [
- "34b-q8_0",
- "36GB"
- ]
- ],
- "image": false,
- "author": "Phind"
- },
"stablelm2": {
"url": "https://ollama.com/library/stablelm2",
"description": "Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.",
@@ -13255,6 +13207,818 @@
"image": false,
"author": "Stability AI"
},
+ "all-minilm": {
+ "url": "https://ollama.com/library/all-minilm",
+ "description": "Embedding models on very large sentence level datasets.",
+ "tags": [
+ [
+ "latest",
+ "46MB"
+ ],
+ [
+ "33m",
+ "67MB"
+ ],
+ [
+ "22m",
+ "46MB"
+ ],
+ [
+ "l12",
+ "67MB"
+ ],
+ [
+ "l6",
+ "46MB"
+ ],
+ [
+ "v2",
+ "46MB"
+ ],
+ [
+ "33m-l12-v2-fp16",
+ "67MB"
+ ],
+ [
+ "22m-l6-v2-fp16",
+ "46MB"
+ ],
+ [
+ "l12-v2",
+ "67MB"
+ ],
+ [
+ "l6-v2",
+ "46MB"
+ ]
+ ],
+ "image": false,
+ "author": "Sentence Transformers"
+ },
+ "granite-code": {
+ "url": "https://ollama.com/library/granite-code",
+ "description": "A family of open foundation models by IBM for Code Intelligence",
+ "tags": [
+ [
+ "latest",
+ "2.0GB"
+ ],
+ [
+ "34b",
+ "19GB"
+ ],
+ [
+ "20b",
+ "12GB"
+ ],
+ [
+ "8b",
+ "4.6GB"
+ ],
+ [
+ "3b",
+ "2.0GB"
+ ],
+ [
+ "34b-base",
+ "19GB"
+ ],
+ [
+ "34b-base-f16",
+ "68GB"
+ ],
+ [
+ "34b-base-q2_K",
+ "13GB"
+ ],
+ [
+ "34b-base-q3_K_L",
+ "20GB"
+ ],
+ [
+ "34b-base-q3_K_M",
+ "18GB"
+ ],
+ [
+ "34b-base-q3_K_S",
+ "15GB"
+ ],
+ [
+ "34b-base-q4_0",
+ "19GB"
+ ],
+ [
+ "34b-base-q4_1",
+ "21GB"
+ ],
+ [
+ "34b-base-q4_K_M",
+ "21GB"
+ ],
+ [
+ "34b-base-q4_K_S",
+ "19GB"
+ ],
+ [
+ "34b-base-q5_0",
+ "23GB"
+ ],
+ [
+ "34b-base-q5_1",
+ "25GB"
+ ],
+ [
+ "34b-base-q5_K_M",
+ "25GB"
+ ],
+ [
+ "34b-base-q5_K_S",
+ "23GB"
+ ],
+ [
+ "34b-base-q6_K",
+ "28GB"
+ ],
+ [
+ "34b-base-q8_0",
+ "36GB"
+ ],
+ [
+ "34b-instruct",
+ "19GB"
+ ],
+ [
+ "34b-instruct-f16",
+ "68GB"
+ ],
+ [
+ "34b-instruct-q2_K",
+ "13GB"
+ ],
+ [
+ "34b-instruct-q3_K_L",
+ "20GB"
+ ],
+ [
+ "34b-instruct-q3_K_M",
+ "18GB"
+ ],
+ [
+ "34b-instruct-q3_K_S",
+ "15GB"
+ ],
+ [
+ "34b-instruct-q4_0",
+ "19GB"
+ ],
+ [
+ "34b-instruct-q4_1",
+ "21GB"
+ ],
+ [
+ "34b-instruct-q4_K_M",
+ "21GB"
+ ],
+ [
+ "34b-instruct-q4_K_S",
+ "19GB"
+ ],
+ [
+ "34b-instruct-q5_0",
+ "23GB"
+ ],
+ [
+ "34b-instruct-q5_1",
+ "25GB"
+ ],
+ [
+ "34b-instruct-q5_K_M",
+ "25GB"
+ ],
+ [
+ "34b-instruct-q5_K_S",
+ "23GB"
+ ],
+ [
+ "34b-instruct-q6_K",
+ "28GB"
+ ],
+ [
+ "34b-instruct-q8_0",
+ "36GB"
+ ],
+ [
+ "20b-base-f16",
+ "40GB"
+ ],
+ [
+ "20b-base",
+ "12GB"
+ ],
+ [
+ "20b-base-fp16",
+ "40GB"
+ ],
+ [
+ "20b-base-q2_K",
+ "7.9GB"
+ ],
+ [
+ "20b-base-q3_K_L",
+ "12GB"
+ ],
+ [
+ "20b-base-q3_K_M",
+ "11GB"
+ ],
+ [
+ "20b-base-q3_K_S",
+ "8.9GB"
+ ],
+ [
+ "20b-base-q4_0",
+ "12GB"
+ ],
+ [
+ "20b-base-q4_1",
+ "13GB"
+ ],
+ [
+ "20b-base-q4_K_M",
+ "13GB"
+ ],
+ [
+ "20b-base-q4_K_S",
+ "12GB"
+ ],
+ [
+ "20b-base-q5_0",
+ "14GB"
+ ],
+ [
+ "20b-base-q5_1",
+ "15GB"
+ ],
+ [
+ "20b-base-q5_K_M",
+ "15GB"
+ ],
+ [
+ "20b-base-q5_K_S",
+ "14GB"
+ ],
+ [
+ "20b-base-q6_K",
+ "17GB"
+ ],
+ [
+ "20b-base-q8_0",
+ "21GB"
+ ],
+ [
+ "20b-instruct-f16",
+ "40GB"
+ ],
+ [
+ "20b-instruct",
+ "12GB"
+ ],
+ [
+ "20b-instruct-q2_K",
+ "7.9GB"
+ ],
+ [
+ "20b-instruct-q3_K_L",
+ "12GB"
+ ],
+ [
+ "20b-instruct-q3_K_M",
+ "11GB"
+ ],
+ [
+ "20b-instruct-q3_K_S",
+ "8.9GB"
+ ],
+ [
+ "20b-instruct-q4_0",
+ "12GB"
+ ],
+ [
+ "20b-instruct-q4_1",
+ "13GB"
+ ],
+ [
+ "20b-instruct-q4_K_M",
+ "13GB"
+ ],
+ [
+ "20b-instruct-q4_K_S",
+ "12GB"
+ ],
+ [
+ "20b-instruct-q5_0",
+ "14GB"
+ ],
+ [
+ "20b-instruct-q5_1",
+ "15GB"
+ ],
+ [
+ "20b-instruct-q5_K_M",
+ "15GB"
+ ],
+ [
+ "20b-instruct-q5_K_S",
+ "14GB"
+ ],
+ [
+ "20b-instruct-q6_K",
+ "17GB"
+ ],
+ [
+ "20b-instruct-q8_0",
+ "21GB"
+ ],
+ [
+ "8b-base",
+ "4.6GB"
+ ],
+ [
+ "8b-base-f16",
+ "16GB"
+ ],
+ [
+ "8b-base-fp16",
+ "16GB"
+ ],
+ [
+ "8b-base-q2_K",
+ "3.1GB"
+ ],
+ [
+ "8b-base-q3_K_L",
+ "4.3GB"
+ ],
+ [
+ "8b-base-q3_K_M",
+ "3.9GB"
+ ],
+ [
+ "8b-base-q3_K_S",
+ "3.5GB"
+ ],
+ [
+ "8b-base-q4_0",
+ "4.6GB"
+ ],
+ [
+ "8b-base-q4_1",
+ "5.1GB"
+ ],
+ [
+ "8b-base-q4_K_M",
+ "4.9GB"
+ ],
+ [
+ "8b-base-q4_K_S",
+ "4.6GB"
+ ],
+ [
+ "8b-base-q5_0",
+ "5.6GB"
+ ],
+ [
+ "8b-base-q5_1",
+ "6.1GB"
+ ],
+ [
+ "8b-base-q5_K_M",
+ "5.7GB"
+ ],
+ [
+ "8b-base-q5_K_S",
+ "5.6GB"
+ ],
+ [
+ "8b-base-q6_K",
+ "6.6GB"
+ ],
+ [
+ "8b-base-q8_0",
+ "8.6GB"
+ ],
+ [
+ "8b-instruct",
+ "4.6GB"
+ ],
+ [
+ "8b-instruct-f16",
+ "16GB"
+ ],
+ [
+ "8b-instruct-fp16",
+ "16GB"
+ ],
+ [
+ "8b-instruct-q2_K",
+ "3.1GB"
+ ],
+ [
+ "8b-instruct-q3_K_L",
+ "4.3GB"
+ ],
+ [
+ "8b-instruct-q3_K_M",
+ "3.9GB"
+ ],
+ [
+ "8b-instruct-q3_K_S",
+ "3.5GB"
+ ],
+ [
+ "8b-instruct-q4_0",
+ "4.6GB"
+ ],
+ [
+ "8b-instruct-q4_1",
+ "5.1GB"
+ ],
+ [
+ "8b-instruct-q4_K_M",
+ "4.9GB"
+ ],
+ [
+ "8b-instruct-q4_K_S",
+ "4.6GB"
+ ],
+ [
+ "8b-instruct-q5_0",
+ "5.6GB"
+ ],
+ [
+ "8b-instruct-q5_1",
+ "6.1GB"
+ ],
+ [
+ "8b-instruct-q5_K_M",
+ "5.7GB"
+ ],
+ [
+ "8b-instruct-q5_K_S",
+ "5.6GB"
+ ],
+ [
+ "8b-instruct-q6_K",
+ "6.6GB"
+ ],
+ [
+ "8b-instruct-q8_0",
+ "8.6GB"
+ ],
+ [
+ "3b-base",
+ "2.0GB"
+ ],
+ [
+ "3b-base-f16",
+ "7.0GB"
+ ],
+ [
+ "3b-base-fp16",
+ "7.0GB"
+ ],
+ [
+ "3b-base-q2_K",
+ "1.3GB"
+ ],
+ [
+ "3b-base-q3_K_L",
+ "1.9GB"
+ ],
+ [
+ "3b-base-q3_K_M",
+ "1.7GB"
+ ],
+ [
+ "3b-base-q3_K_S",
+ "1.6GB"
+ ],
+ [
+ "3b-base-q4_0",
+ "2.0GB"
+ ],
+ [
+ "3b-base-q4_1",
+ "2.2GB"
+ ],
+ [
+ "3b-base-q4_K_M",
+ "2.1GB"
+ ],
+ [
+ "3b-base-q4_K_S",
+ "2.0GB"
+ ],
+ [
+ "3b-base-q5_0",
+ "2.4GB"
+ ],
+ [
+ "3b-base-q5_1",
+ "2.6GB"
+ ],
+ [
+ "3b-base-q5_K_M",
+ "2.5GB"
+ ],
+ [
+ "3b-base-q5_K_S",
+ "2.4GB"
+ ],
+ [
+ "3b-base-q6_K",
+ "2.9GB"
+ ],
+ [
+ "3b-base-q8_0",
+ "3.7GB"
+ ],
+ [
+ "3b-instruct-f16",
+ "7.0GB"
+ ],
+ [
+ "3b-instruct",
+ "2.0GB"
+ ],
+ [
+ "3b-instruct-fp16",
+ "7.0GB"
+ ],
+ [
+ "3b-instruct-q2_K",
+ "1.3GB"
+ ],
+ [
+ "3b-instruct-q3_K_L",
+ "1.9GB"
+ ],
+ [
+ "3b-instruct-q3_K_M",
+ "1.7GB"
+ ],
+ [
+ "3b-instruct-q3_K_S",
+ "1.6GB"
+ ],
+ [
+ "3b-instruct-q4_0",
+ "2.0GB"
+ ],
+ [
+ "3b-instruct-q4_1",
+ "2.2GB"
+ ],
+ [
+ "3b-instruct-q4_K_M",
+ "2.1GB"
+ ],
+ [
+ "3b-instruct-q4_K_S",
+ "2.0GB"
+ ],
+ [
+ "3b-instruct-q5_0",
+ "2.4GB"
+ ],
+ [
+ "3b-instruct-q5_1",
+ "2.6GB"
+ ],
+ [
+ "3b-instruct-q5_K_M",
+ "2.5GB"
+ ],
+ [
+ "3b-instruct-q5_K_S",
+ "2.4GB"
+ ],
+ [
+ "3b-instruct-q6_K",
+ "2.9GB"
+ ],
+ [
+ "3b-instruct-q8_0",
+ "3.7GB"
+ ]
+ ],
+ "image": false,
+ "author": "IBM for Code Intelligence"
+ },
+ "phind-codellama": {
+ "url": "https://ollama.com/library/phind-codellama",
+ "description": "Code generation model based on Code Llama.",
+ "tags": [
+ [
+ "latest",
+ "19GB"
+ ],
+ [
+ "34b",
+ "19GB"
+ ],
+ [
+ "34b-python",
+ "19GB"
+ ],
+ [
+ "34b-python-fp16",
+ "67GB"
+ ],
+ [
+ "34b-python-q2_K",
+ "14GB"
+ ],
+ [
+ "34b-python-q3_K_L",
+ "18GB"
+ ],
+ [
+ "34b-python-q3_K_M",
+ "16GB"
+ ],
+ [
+ "34b-python-q3_K_S",
+ "15GB"
+ ],
+ [
+ "34b-python-q4_0",
+ "19GB"
+ ],
+ [
+ "34b-python-q4_1",
+ "21GB"
+ ],
+ [
+ "34b-python-q4_K_M",
+ "20GB"
+ ],
+ [
+ "34b-python-q4_K_S",
+ "19GB"
+ ],
+ [
+ "34b-python-q5_0",
+ "23GB"
+ ],
+ [
+ "34b-python-q5_1",
+ "25GB"
+ ],
+ [
+ "34b-python-q5_K_M",
+ "24GB"
+ ],
+ [
+ "34b-python-q5_K_S",
+ "23GB"
+ ],
+ [
+ "34b-python-q6_K",
+ "28GB"
+ ],
+ [
+ "34b-python-q8_0",
+ "36GB"
+ ],
+ [
+ "34b-v2",
+ "19GB"
+ ],
+ [
+ "34b-v2-fp16",
+ "67GB"
+ ],
+ [
+ "34b-v2-q2_K",
+ "14GB"
+ ],
+ [
+ "34b-v2-q3_K_L",
+ "18GB"
+ ],
+ [
+ "34b-v2-q3_K_M",
+ "16GB"
+ ],
+ [
+ "34b-v2-q3_K_S",
+ "15GB"
+ ],
+ [
+ "34b-v2-q4_0",
+ "19GB"
+ ],
+ [
+ "34b-v2-q4_1",
+ "21GB"
+ ],
+ [
+ "34b-v2-q4_K_M",
+ "20GB"
+ ],
+ [
+ "34b-v2-q4_K_S",
+ "19GB"
+ ],
+ [
+ "34b-v2-q5_0",
+ "23GB"
+ ],
+ [
+ "34b-v2-q5_1",
+ "25GB"
+ ],
+ [
+ "34b-v2-q5_K_M",
+ "24GB"
+ ],
+ [
+ "34b-v2-q5_K_S",
+ "23GB"
+ ],
+ [
+ "34b-v2-q6_K",
+ "28GB"
+ ],
+ [
+ "34b-v2-q8_0",
+ "36GB"
+ ],
+ [
+ "34b-fp16",
+ "67GB"
+ ],
+ [
+ "34b-q2_K",
+ "14GB"
+ ],
+ [
+ "34b-q3_K_L",
+ "18GB"
+ ],
+ [
+ "34b-q3_K_M",
+ "16GB"
+ ],
+ [
+ "34b-q3_K_S",
+ "15GB"
+ ],
+ [
+ "34b-q4_0",
+ "19GB"
+ ],
+ [
+ "34b-q4_1",
+ "21GB"
+ ],
+ [
+ "34b-q4_K_M",
+ "20GB"
+ ],
+ [
+ "34b-q4_K_S",
+ "19GB"
+ ],
+ [
+ "34b-q5_0",
+ "23GB"
+ ],
+ [
+ "34b-q5_1",
+ "25GB"
+ ],
+ [
+ "34b-q5_K_M",
+ "24GB"
+ ],
+ [
+ "34b-q5_K_S",
+ "23GB"
+ ],
+ [
+ "34b-q6_K",
+ "28GB"
+ ],
+ [
+ "34b-q8_0",
+ "36GB"
+ ]
+ ],
+ "image": false,
+ "author": "Phind"
+ },
"dolphincoder": {
"url": "https://ollama.com/library/dolphincoder",
"description": "A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.",
@@ -13403,54 +14167,6 @@
"image": false,
"author": "Cognitive Computations"
},
- "all-minilm": {
- "url": "https://ollama.com/library/all-minilm",
- "description": "Embedding models on very large sentence level datasets.",
- "tags": [
- [
- "latest",
- "46MB"
- ],
- [
- "33m",
- "67MB"
- ],
- [
- "22m",
- "46MB"
- ],
- [
- "l12",
- "67MB"
- ],
- [
- "l6",
- "46MB"
- ],
- [
- "v2",
- "46MB"
- ],
- [
- "33m-l12-v2-fp16",
- "67MB"
- ],
- [
- "22m-l6-v2-fp16",
- "46MB"
- ],
- [
- "l12-v2",
- "67MB"
- ],
- [
- "l6-v2",
- "46MB"
- ]
- ],
- "image": false,
- "author": "Sentence Transformers"
- },
"nous-hermes": {
"url": "https://ollama.com/library/nous-hermes",
"description": "General use models based on Llama and Llama 2 from Nous Research.",
@@ -13711,158 +14427,6 @@
"image": false,
"author": "Nous Research"
},
- "starling-lm": {
- "url": "https://ollama.com/library/starling-lm",
- "description": "Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.",
- "tags": [
- [
- "latest",
- "4.1GB"
- ],
- [
- "7b",
- "4.1GB"
- ],
- [
- "alpha",
- "4.1GB"
- ],
- [
- "beta",
- "4.1GB"
- ],
- [
- "7b-alpha",
- "4.1GB"
- ],
- [
- "7b-alpha-fp16",
- "14GB"
- ],
- [
- "7b-alpha-q2_K",
- "2.7GB"
- ],
- [
- "7b-alpha-q3_K_L",
- "3.8GB"
- ],
- [
- "7b-alpha-q3_K_M",
- "3.5GB"
- ],
- [
- "7b-alpha-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-alpha-q4_0",
- "4.1GB"
- ],
- [
- "7b-alpha-q4_1",
- "4.6GB"
- ],
- [
- "7b-alpha-q4_K_M",
- "4.4GB"
- ],
- [
- "7b-alpha-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-alpha-q5_0",
- "5.0GB"
- ],
- [
- "7b-alpha-q5_1",
- "5.4GB"
- ],
- [
- "7b-alpha-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-alpha-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-alpha-q6_K",
- "5.9GB"
- ],
- [
- "7b-alpha-q8_0",
- "7.7GB"
- ],
- [
- "7b-beta",
- "4.1GB"
- ],
- [
- "7b-beta-fp16",
- "14GB"
- ],
- [
- "7b-beta-q2_K",
- "2.7GB"
- ],
- [
- "7b-beta-q3_K_L",
- "3.8GB"
- ],
- [
- "7b-beta-q3_K_M",
- "3.5GB"
- ],
- [
- "7b-beta-q3_K_S",
- "3.2GB"
- ],
- [
- "7b-beta-q4_0",
- "4.1GB"
- ],
- [
- "7b-beta-q4_1",
- "4.6GB"
- ],
- [
- "7b-beta-q4_K_M",
- "4.4GB"
- ],
- [
- "7b-beta-q4_K_S",
- "4.1GB"
- ],
- [
- "7b-beta-q5_0",
- "5.0GB"
- ],
- [
- "7b-beta-q5_1",
- "5.4GB"
- ],
- [
- "7b-beta-q5_K_M",
- "5.1GB"
- ],
- [
- "7b-beta-q5_K_S",
- "5.0GB"
- ],
- [
- "7b-beta-q6_K",
- "5.9GB"
- ],
- [
- "7b-beta-q8_0",
- "7.7GB"
- ]
- ],
- "image": false,
- "author": "Berkeley Nest"
- },
"sqlcoder": {
"url": "https://ollama.com/library/sqlcoder",
"description": "SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks",
@@ -14063,146 +14627,6 @@
"image": false,
"author": "Defog.ai"
},
- "orca2": {
- "url": "https://ollama.com/library/orca2",
- "description": "Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.",
- "tags": [
- [
- "latest",
- "3.8GB"
- ],
- [
- "13b",
- "7.4GB"
- ],
- [
- "7b",
- "3.8GB"
- ],
- [
- "13b-fp16",
- "26GB"
- ],
- [
- "13b-q2_K",
- "5.4GB"
- ],
- [
- "13b-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-q4_0",
- "7.4GB"
- ],
- [
- "13b-q4_1",
- "8.2GB"
- ],
- [
- "13b-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-q5_0",
- "9.0GB"
- ],
- [
- "13b-q5_1",
- "9.8GB"
- ],
- [
- "13b-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-q6_K",
- "11GB"
- ],
- [
- "13b-q8_0",
- "14GB"
- ],
- [
- "7b-fp16",
- "13GB"
- ],
- [
- "7b-q2_K",
- "2.8GB"
- ],
- [
- "7b-q3_K_L",
- "3.6GB"
- ],
- [
- "7b-q3_K_M",
- "3.3GB"
- ],
- [
- "7b-q3_K_S",
- "2.9GB"
- ],
- [
- "7b-q4_0",
- "3.8GB"
- ],
- [
- "7b-q4_1",
- "4.2GB"
- ],
- [
- "7b-q4_K_M",
- "4.1GB"
- ],
- [
- "7b-q4_K_S",
- "3.9GB"
- ],
- [
- "7b-q5_0",
- "4.7GB"
- ],
- [
- "7b-q5_1",
- "5.1GB"
- ],
- [
- "7b-q5_K_M",
- "4.8GB"
- ],
- [
- "7b-q5_K_S",
- "4.7GB"
- ],
- [
- "7b-q6_K",
- "5.5GB"
- ],
- [
- "7b-q8_0",
- "7.2GB"
- ]
- ],
- "image": false,
- "author": "Microsoft Research"
- },
"llama3-gradient": {
"url": "https://ollama.com/library/llama3-gradient",
"description": "This model extends LLama-3 8B's context length from 8k to over 1m tokens.",
@@ -14351,6 +14775,158 @@
"image": false,
"author": "Gradient AI"
},
+ "starling-lm": {
+ "url": "https://ollama.com/library/starling-lm",
+ "description": "Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.",
+ "tags": [
+ [
+ "latest",
+ "4.1GB"
+ ],
+ [
+ "7b",
+ "4.1GB"
+ ],
+ [
+ "alpha",
+ "4.1GB"
+ ],
+ [
+ "beta",
+ "4.1GB"
+ ],
+ [
+ "7b-alpha",
+ "4.1GB"
+ ],
+ [
+ "7b-alpha-fp16",
+ "14GB"
+ ],
+ [
+ "7b-alpha-q2_K",
+ "2.7GB"
+ ],
+ [
+ "7b-alpha-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-alpha-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-alpha-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-alpha-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-alpha-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-alpha-q4_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-alpha-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-alpha-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-alpha-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-alpha-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-alpha-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-alpha-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-alpha-q8_0",
+ "7.7GB"
+ ],
+ [
+ "7b-beta",
+ "4.1GB"
+ ],
+ [
+ "7b-beta-fp16",
+ "14GB"
+ ],
+ [
+ "7b-beta-q2_K",
+ "2.7GB"
+ ],
+ [
+ "7b-beta-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-beta-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-beta-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-beta-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-beta-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-beta-q4_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-beta-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-beta-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-beta-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-beta-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-beta-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-beta-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-beta-q8_0",
+ "7.7GB"
+ ]
+ ],
+ "image": false,
+ "author": "Berkeley Nest"
+ },
"deepseek-llm": {
"url": "https://ollama.com/library/deepseek-llm",
"description": "An advanced language model crafted with 2 trillion bilingual tokens.",
@@ -14891,290 +15467,6 @@
"image": false,
"author": "Nous Research"
},
- "llama3-chatqa": {
- "url": "https://ollama.com/library/llama3-chatqa",
- "description": "A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).",
- "tags": [
- [
- "latest",
- "4.7GB"
- ],
- [
- "70b",
- "40GB"
- ],
- [
- "8b",
- "4.7GB"
- ],
- [
- "70b-v1.5",
- "40GB"
- ],
- [
- "70b-v1.5-fp16",
- "141GB"
- ],
- [
- "70b-v1.5-q2_K",
- "26GB"
- ],
- [
- "70b-v1.5-q3_K_L",
- "37GB"
- ],
- [
- "70b-v1.5-q3_K_M",
- "34GB"
- ],
- [
- "70b-v1.5-q3_K_S",
- "31GB"
- ],
- [
- "70b-v1.5-q4_0",
- "40GB"
- ],
- [
- "70b-v1.5-q4_1",
- "44GB"
- ],
- [
- "70b-v1.5-q4_K_M",
- "43GB"
- ],
- [
- "70b-v1.5-q4_K_S",
- "40GB"
- ],
- [
- "70b-v1.5-q5_0",
- "49GB"
- ],
- [
- "70b-v1.5-q5_1",
- "53GB"
- ],
- [
- "70b-v1.5-q5_K_M",
- "50GB"
- ],
- [
- "70b-v1.5-q5_K_S",
- "49GB"
- ],
- [
- "70b-v1.5-q6_K",
- "58GB"
- ],
- [
- "70b-v1.5-q8_0",
- "75GB"
- ],
- [
- "8b-v1.5",
- "4.7GB"
- ],
- [
- "8b-v1.5-fp16",
- "16GB"
- ],
- [
- "8b-v1.5-q2_K",
- "3.2GB"
- ],
- [
- "8b-v1.5-q3_K_L",
- "4.3GB"
- ],
- [
- "8b-v1.5-q3_K_M",
- "4.0GB"
- ],
- [
- "8b-v1.5-q3_K_S",
- "3.7GB"
- ],
- [
- "8b-v1.5-q4_0",
- "4.7GB"
- ],
- [
- "8b-v1.5-q4_1",
- "5.1GB"
- ],
- [
- "8b-v1.5-q4_K_M",
- "4.9GB"
- ],
- [
- "8b-v1.5-q4_K_S",
- "4.7GB"
- ],
- [
- "8b-v1.5-q5_0",
- "5.6GB"
- ],
- [
- "8b-v1.5-q5_1",
- "6.1GB"
- ],
- [
- "8b-v1.5-q5_K_M",
- "5.7GB"
- ],
- [
- "8b-v1.5-q5_K_S",
- "5.6GB"
- ],
- [
- "8b-v1.5-q6_K",
- "6.6GB"
- ],
- [
- "8b-v1.5-q8_0",
- "8.5GB"
- ]
- ],
- "image": false,
- "author": "Nvidia"
- },
- "solar": {
- "url": "https://ollama.com/library/solar",
- "description": "A compact, yet powerful 10.7B large language model designed for single-turn conversation.",
- "tags": [
- [
- "latest",
- "6.1GB"
- ],
- [
- "10.7b",
- "6.1GB"
- ],
- [
- "10.7b-instruct-v1-fp16",
- "21GB"
- ],
- [
- "10.7b-instruct-v1-q2_K",
- "4.5GB"
- ],
- [
- "10.7b-instruct-v1-q3_K_L",
- "5.7GB"
- ],
- [
- "10.7b-instruct-v1-q3_K_M",
- "5.2GB"
- ],
- [
- "10.7b-instruct-v1-q3_K_S",
- "4.7GB"
- ],
- [
- "10.7b-instruct-v1-q4_0",
- "6.1GB"
- ],
- [
- "10.7b-instruct-v1-q4_1",
- "6.7GB"
- ],
- [
- "10.7b-instruct-v1-q4_K_M",
- "6.5GB"
- ],
- [
- "10.7b-instruct-v1-q4_K_S",
- "6.1GB"
- ],
- [
- "10.7b-instruct-v1-q5_0",
- "7.4GB"
- ],
- [
- "10.7b-instruct-v1-q5_1",
- "8.1GB"
- ],
- [
- "10.7b-instruct-v1-q5_K_M",
- "7.6GB"
- ],
- [
- "10.7b-instruct-v1-q5_K_S",
- "7.4GB"
- ],
- [
- "10.7b-instruct-v1-q6_K",
- "8.8GB"
- ],
- [
- "10.7b-instruct-v1-q8_0",
- "11GB"
- ],
- [
- "10.7b-text-v1-fp16",
- "21GB"
- ],
- [
- "10.7b-text-v1-q2_K",
- "4.5GB"
- ],
- [
- "10.7b-text-v1-q3_K_L",
- "5.7GB"
- ],
- [
- "10.7b-text-v1-q3_K_M",
- "5.2GB"
- ],
- [
- "10.7b-text-v1-q3_K_S",
- "4.7GB"
- ],
- [
- "10.7b-text-v1-q4_0",
- "6.1GB"
- ],
- [
- "10.7b-text-v1-q4_1",
- "6.7GB"
- ],
- [
- "10.7b-text-v1-q4_K_M",
- "6.5GB"
- ],
- [
- "10.7b-text-v1-q4_K_S",
- "6.1GB"
- ],
- [
- "10.7b-text-v1-q5_0",
- "7.4GB"
- ],
- [
- "10.7b-text-v1-q5_1",
- "8.1GB"
- ],
- [
- "10.7b-text-v1-q5_K_M",
- "7.6GB"
- ],
- [
- "10.7b-text-v1-q5_K_S",
- "7.4GB"
- ],
- [
- "10.7b-text-v1-q6_K",
- "8.8GB"
- ],
- [
- "10.7b-text-v1-q8_0",
- "11GB"
- ]
- ],
- "image": false,
- "author": "Upstage"
- },
"xwinlm": {
"url": "https://ollama.com/library/xwinlm",
"description": "Conversational model based on Llama 2 that performs competitively on various benchmarks.",
@@ -15503,633 +15795,429 @@
"image": false,
"author": "Xwin LM"
},
- "granite-code": {
- "url": "https://ollama.com/library/granite-code",
- "description": "A family of open foundation models by IBM for Code Intelligence",
+ "llama3-chatqa": {
+ "url": "https://ollama.com/library/llama3-chatqa",
+ "description": "A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).",
"tags": [
[
"latest",
- "2.0GB"
+ "4.7GB"
],
[
- "34b",
- "19GB"
- ],
- [
- "20b",
- "12GB"
+ "70b",
+ "40GB"
],
[
"8b",
- "4.6GB"
+ "4.7GB"
],
[
- "3b",
- "2.0GB"
- ],
- [
- "34b-base",
- "19GB"
- ],
- [
- "34b-base-f16",
- "68GB"
- ],
- [
- "34b-base-q2_K",
- "13GB"
- ],
- [
- "34b-base-q3_K_L",
- "20GB"
- ],
- [
- "34b-base-q3_K_M",
- "18GB"
- ],
- [
- "34b-base-q3_K_S",
- "15GB"
- ],
- [
- "34b-base-q4_0",
- "19GB"
- ],
- [
- "34b-base-q4_1",
- "21GB"
- ],
- [
- "34b-base-q4_K_M",
- "21GB"
- ],
- [
- "34b-base-q4_K_S",
- "19GB"
- ],
- [
- "34b-base-q5_0",
- "23GB"
- ],
- [
- "34b-base-q5_1",
- "25GB"
- ],
- [
- "34b-base-q5_K_M",
- "25GB"
- ],
- [
- "34b-base-q5_K_S",
- "23GB"
- ],
- [
- "34b-base-q6_K",
- "28GB"
- ],
- [
- "34b-base-q8_0",
- "36GB"
- ],
- [
- "34b-instruct-f16",
- "68GB"
- ],
- [
- "34b-instruct",
- "19GB"
- ],
- [
- "34b-instruct-q2_K",
- "13GB"
- ],
- [
- "34b-instruct-q3_K_L",
- "20GB"
- ],
- [
- "34b-instruct-q3_K_M",
- "18GB"
- ],
- [
- "34b-instruct-q3_K_S",
- "15GB"
- ],
- [
- "34b-instruct-q4_0",
- "19GB"
- ],
- [
- "34b-instruct-q4_1",
- "21GB"
- ],
- [
- "34b-instruct-q4_K_M",
- "21GB"
- ],
- [
- "34b-instruct-q4_K_S",
- "19GB"
- ],
- [
- "34b-instruct-q5_0",
- "23GB"
- ],
- [
- "34b-instruct-q5_1",
- "25GB"
- ],
- [
- "34b-instruct-q5_K_M",
- "25GB"
- ],
- [
- "34b-instruct-q5_K_S",
- "23GB"
- ],
- [
- "34b-instruct-q6_K",
- "28GB"
- ],
- [
- "34b-instruct-q8_0",
- "36GB"
- ],
- [
- "20b-base",
- "12GB"
- ],
- [
- "20b-base-f16",
+ "70b-v1.5",
"40GB"
],
[
- "20b-base-fp16",
+ "70b-v1.5-fp16",
+ "141GB"
+ ],
+ [
+ "70b-v1.5-q2_K",
+ "26GB"
+ ],
+ [
+ "70b-v1.5-q3_K_L",
+ "37GB"
+ ],
+ [
+ "70b-v1.5-q3_K_M",
+ "34GB"
+ ],
+ [
+ "70b-v1.5-q3_K_S",
+ "31GB"
+ ],
+ [
+ "70b-v1.5-q4_0",
"40GB"
],
[
- "20b-base-q2_K",
- "7.9GB"
+ "70b-v1.5-q4_1",
+ "44GB"
],
[
- "20b-base-q3_K_L",
- "12GB"
+ "70b-v1.5-q4_K_M",
+ "43GB"
],
[
- "20b-base-q3_K_M",
- "11GB"
- ],
- [
- "20b-base-q3_K_S",
- "8.9GB"
- ],
- [
- "20b-base-q4_0",
- "12GB"
- ],
- [
- "20b-base-q4_1",
- "13GB"
- ],
- [
- "20b-base-q4_K_M",
- "13GB"
- ],
- [
- "20b-base-q4_K_S",
- "12GB"
- ],
- [
- "20b-base-q5_0",
- "14GB"
- ],
- [
- "20b-base-q5_1",
- "15GB"
- ],
- [
- "20b-base-q5_K_M",
- "15GB"
- ],
- [
- "20b-base-q5_K_S",
- "14GB"
- ],
- [
- "20b-base-q6_K",
- "17GB"
- ],
- [
- "20b-base-q8_0",
- "21GB"
- ],
- [
- "20b-instruct-f16",
+ "70b-v1.5-q4_K_S",
"40GB"
],
[
- "20b-instruct",
- "12GB"
+ "70b-v1.5-q5_0",
+ "49GB"
],
[
- "20b-instruct-q2_K",
- "7.9GB"
+ "70b-v1.5-q5_1",
+ "53GB"
],
[
- "20b-instruct-q3_K_L",
- "12GB"
+ "70b-v1.5-q5_K_M",
+ "50GB"
],
[
- "20b-instruct-q3_K_M",
- "11GB"
+ "70b-v1.5-q5_K_S",
+ "49GB"
],
[
- "20b-instruct-q3_K_S",
- "8.9GB"
+ "70b-v1.5-q6_K",
+ "58GB"
],
[
- "20b-instruct-q4_0",
- "12GB"
+ "70b-v1.5-q8_0",
+ "75GB"
],
[
- "20b-instruct-q4_1",
- "13GB"
+ "8b-v1.5",
+ "4.7GB"
],
[
- "20b-instruct-q4_K_M",
- "13GB"
- ],
- [
- "20b-instruct-q4_K_S",
- "12GB"
- ],
- [
- "20b-instruct-q5_0",
- "14GB"
- ],
- [
- "20b-instruct-q5_1",
- "15GB"
- ],
- [
- "20b-instruct-q5_K_M",
- "15GB"
- ],
- [
- "20b-instruct-q5_K_S",
- "14GB"
- ],
- [
- "20b-instruct-q6_K",
- "17GB"
- ],
- [
- "20b-instruct-q8_0",
- "21GB"
- ],
- [
- "8b-base",
- "4.6GB"
- ],
- [
- "8b-base-f16",
+ "8b-v1.5-fp16",
"16GB"
],
[
- "8b-base-fp16",
- "16GB"
+ "8b-v1.5-q2_K",
+ "3.2GB"
],
[
- "8b-base-q2_K",
- "3.1GB"
- ],
- [
- "8b-base-q3_K_L",
+ "8b-v1.5-q3_K_L",
"4.3GB"
],
[
- "8b-base-q3_K_M",
- "3.9GB"
+ "8b-v1.5-q3_K_M",
+ "4.0GB"
],
[
- "8b-base-q3_K_S",
- "3.5GB"
- ],
- [
- "8b-base-q4_0",
- "4.6GB"
- ],
- [
- "8b-base-q4_1",
- "5.1GB"
- ],
- [
- "8b-base-q4_K_M",
- "4.9GB"
- ],
- [
- "8b-base-q4_K_S",
- "4.6GB"
- ],
- [
- "8b-base-q5_0",
- "5.6GB"
- ],
- [
- "8b-base-q5_1",
- "6.1GB"
- ],
- [
- "8b-base-q5_K_M",
- "5.7GB"
- ],
- [
- "8b-base-q5_K_S",
- "5.6GB"
- ],
- [
- "8b-base-q6_K",
- "6.6GB"
- ],
- [
- "8b-base-q8_0",
- "8.6GB"
- ],
- [
- "8b-instruct-f16",
- "16GB"
- ],
- [
- "8b-instruct",
- "4.6GB"
- ],
- [
- "8b-instruct-fp16",
- "16GB"
- ],
- [
- "8b-instruct-q2_K",
- "3.1GB"
- ],
- [
- "8b-instruct-q3_K_L",
- "4.3GB"
- ],
- [
- "8b-instruct-q3_K_M",
- "3.9GB"
- ],
- [
- "8b-instruct-q3_K_S",
- "3.5GB"
- ],
- [
- "8b-instruct-q4_0",
- "4.6GB"
- ],
- [
- "8b-instruct-q4_1",
- "5.1GB"
- ],
- [
- "8b-instruct-q4_K_M",
- "4.9GB"
- ],
- [
- "8b-instruct-q4_K_S",
- "4.6GB"
- ],
- [
- "8b-instruct-q5_0",
- "5.6GB"
- ],
- [
- "8b-instruct-q5_1",
- "6.1GB"
- ],
- [
- "8b-instruct-q5_K_M",
- "5.7GB"
- ],
- [
- "8b-instruct-q5_K_S",
- "5.6GB"
- ],
- [
- "8b-instruct-q6_K",
- "6.6GB"
- ],
- [
- "8b-instruct-q8_0",
- "8.6GB"
- ],
- [
- "3b-base-f16",
- "7.0GB"
- ],
- [
- "3b-base",
- "2.0GB"
- ],
- [
- "3b-base-fp16",
- "7.0GB"
- ],
- [
- "3b-base-q2_K",
- "1.3GB"
- ],
- [
- "3b-base-q3_K_L",
- "1.9GB"
- ],
- [
- "3b-base-q3_K_M",
- "1.7GB"
- ],
- [
- "3b-base-q3_K_S",
- "1.6GB"
- ],
- [
- "3b-base-q4_0",
- "2.0GB"
- ],
- [
- "3b-base-q4_1",
- "2.2GB"
- ],
- [
- "3b-base-q4_K_M",
- "2.1GB"
- ],
- [
- "3b-base-q4_K_S",
- "2.0GB"
- ],
- [
- "3b-base-q5_0",
- "2.4GB"
- ],
- [
- "3b-base-q5_1",
- "2.6GB"
- ],
- [
- "3b-base-q5_K_M",
- "2.5GB"
- ],
- [
- "3b-base-q5_K_S",
- "2.4GB"
- ],
- [
- "3b-base-q6_K",
- "2.9GB"
- ],
- [
- "3b-base-q8_0",
+ "8b-v1.5-q3_K_S",
"3.7GB"
],
[
- "3b-instruct-f16",
- "7.0GB"
+ "8b-v1.5-q4_0",
+ "4.7GB"
],
[
- "3b-instruct",
- "2.0GB"
+ "8b-v1.5-q4_1",
+ "5.1GB"
],
[
- "3b-instruct-fp16",
- "7.0GB"
+ "8b-v1.5-q4_K_M",
+ "4.9GB"
],
[
- "3b-instruct-q2_K",
- "1.3GB"
+ "8b-v1.5-q4_K_S",
+ "4.7GB"
],
[
- "3b-instruct-q3_K_L",
- "1.9GB"
+ "8b-v1.5-q5_0",
+ "5.6GB"
],
[
- "3b-instruct-q3_K_M",
- "1.7GB"
+ "8b-v1.5-q5_1",
+ "6.1GB"
],
[
- "3b-instruct-q3_K_S",
- "1.6GB"
+ "8b-v1.5-q5_K_M",
+ "5.7GB"
],
[
- "3b-instruct-q4_0",
- "2.0GB"
+ "8b-v1.5-q5_K_S",
+ "5.6GB"
],
[
- "3b-instruct-q4_1",
- "2.2GB"
+ "8b-v1.5-q6_K",
+ "6.6GB"
],
[
- "3b-instruct-q4_K_M",
- "2.1GB"
- ],
- [
- "3b-instruct-q4_K_S",
- "2.0GB"
- ],
- [
- "3b-instruct-q5_0",
- "2.4GB"
- ],
- [
- "3b-instruct-q5_1",
- "2.6GB"
- ],
- [
- "3b-instruct-q5_K_M",
- "2.5GB"
- ],
- [
- "3b-instruct-q5_K_S",
- "2.4GB"
- ],
- [
- "3b-instruct-q6_K",
- "2.9GB"
- ],
- [
- "3b-instruct-q8_0",
- "3.7GB"
+ "8b-v1.5-q8_0",
+ "8.5GB"
]
],
"image": false,
- "author": "IBM for Code Intelligence"
+ "author": "Nvidia"
},
- "dolphin-phi": {
- "url": "https://ollama.com/library/dolphin-phi",
- "description": "2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.",
+ "orca2": {
+ "url": "https://ollama.com/library/orca2",
+ "description": "Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.",
"tags": [
[
"latest",
- "1.6GB"
+ "3.8GB"
],
[
- "2.7b",
- "1.6GB"
+ "13b",
+ "7.4GB"
],
[
- "2.7b-v2.6",
- "1.6GB"
+ "7b",
+ "3.8GB"
],
[
- "2.7b-v2.6-q2_K",
- "1.2GB"
+ "13b-fp16",
+ "26GB"
],
[
- "2.7b-v2.6-q3_K_L",
- "1.6GB"
+ "13b-q2_K",
+ "5.4GB"
],
[
- "2.7b-v2.6-q3_K_M",
- "1.5GB"
+ "13b-q3_K_L",
+ "6.9GB"
],
[
- "2.7b-v2.6-q3_K_S",
- "1.3GB"
+ "13b-q3_K_M",
+ "6.3GB"
],
[
- "2.7b-v2.6-q4_0",
- "1.6GB"
+ "13b-q3_K_S",
+ "5.7GB"
],
[
- "2.7b-v2.6-q4_K_M",
- "1.8GB"
+ "13b-q4_0",
+ "7.4GB"
],
[
- "2.7b-v2.6-q4_K_S",
- "1.6GB"
+ "13b-q4_1",
+ "8.2GB"
],
[
- "2.7b-v2.6-q5_0",
- "1.9GB"
+ "13b-q4_K_M",
+ "7.9GB"
],
[
- "2.7b-v2.6-q5_K_M",
- "2.1GB"
+ "13b-q4_K_S",
+ "7.4GB"
],
[
- "2.7b-v2.6-q5_K_S",
- "1.9GB"
+ "13b-q5_0",
+ "9.0GB"
],
[
- "2.7b-v2.6-q6_K",
- "2.3GB"
+ "13b-q5_1",
+ "9.8GB"
],
[
- "2.7b-v2.6-q8_0",
- "3.0GB"
+ "13b-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-q8_0",
+ "14GB"
+ ],
+ [
+ "7b-fp16",
+ "13GB"
+ ],
+ [
+ "7b-q2_K",
+ "2.8GB"
+ ],
+ [
+ "7b-q3_K_L",
+ "3.6GB"
+ ],
+ [
+ "7b-q3_K_M",
+ "3.3GB"
+ ],
+ [
+ "7b-q3_K_S",
+ "2.9GB"
+ ],
+ [
+ "7b-q4_0",
+ "3.8GB"
+ ],
+ [
+ "7b-q4_1",
+ "4.2GB"
+ ],
+ [
+ "7b-q4_K_M",
+ "4.1GB"
+ ],
+ [
+ "7b-q4_K_S",
+ "3.9GB"
+ ],
+ [
+ "7b-q5_0",
+ "4.7GB"
+ ],
+ [
+ "7b-q5_1",
+ "5.1GB"
+ ],
+ [
+ "7b-q5_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-q5_K_S",
+ "4.7GB"
+ ],
+ [
+ "7b-q6_K",
+ "5.5GB"
+ ],
+ [
+ "7b-q8_0",
+ "7.2GB"
]
],
"image": false,
- "author": "Eric Hartford"
+ "author": "Microsoft Research"
+ },
+ "solar": {
+ "url": "https://ollama.com/library/solar",
+ "description": "A compact, yet powerful 10.7B large language model designed for single-turn conversation.",
+ "tags": [
+ [
+ "latest",
+ "6.1GB"
+ ],
+ [
+ "10.7b",
+ "6.1GB"
+ ],
+ [
+ "10.7b-instruct-v1-fp16",
+ "21GB"
+ ],
+ [
+ "10.7b-instruct-v1-q2_K",
+ "4.5GB"
+ ],
+ [
+ "10.7b-instruct-v1-q3_K_L",
+ "5.7GB"
+ ],
+ [
+ "10.7b-instruct-v1-q3_K_M",
+ "5.2GB"
+ ],
+ [
+ "10.7b-instruct-v1-q3_K_S",
+ "4.7GB"
+ ],
+ [
+ "10.7b-instruct-v1-q4_0",
+ "6.1GB"
+ ],
+ [
+ "10.7b-instruct-v1-q4_1",
+ "6.7GB"
+ ],
+ [
+ "10.7b-instruct-v1-q4_K_M",
+ "6.5GB"
+ ],
+ [
+ "10.7b-instruct-v1-q4_K_S",
+ "6.1GB"
+ ],
+ [
+ "10.7b-instruct-v1-q5_0",
+ "7.4GB"
+ ],
+ [
+ "10.7b-instruct-v1-q5_1",
+ "8.1GB"
+ ],
+ [
+ "10.7b-instruct-v1-q5_K_M",
+ "7.6GB"
+ ],
+ [
+ "10.7b-instruct-v1-q5_K_S",
+ "7.4GB"
+ ],
+ [
+ "10.7b-instruct-v1-q6_K",
+ "8.8GB"
+ ],
+ [
+ "10.7b-instruct-v1-q8_0",
+ "11GB"
+ ],
+ [
+ "10.7b-text-v1-fp16",
+ "21GB"
+ ],
+ [
+ "10.7b-text-v1-q2_K",
+ "4.5GB"
+ ],
+ [
+ "10.7b-text-v1-q3_K_L",
+ "5.7GB"
+ ],
+ [
+ "10.7b-text-v1-q3_K_M",
+ "5.2GB"
+ ],
+ [
+ "10.7b-text-v1-q3_K_S",
+ "4.7GB"
+ ],
+ [
+ "10.7b-text-v1-q4_0",
+ "6.1GB"
+ ],
+ [
+ "10.7b-text-v1-q4_1",
+ "6.7GB"
+ ],
+ [
+ "10.7b-text-v1-q4_K_M",
+ "6.5GB"
+ ],
+ [
+ "10.7b-text-v1-q4_K_S",
+ "6.1GB"
+ ],
+ [
+ "10.7b-text-v1-q5_0",
+ "7.4GB"
+ ],
+ [
+ "10.7b-text-v1-q5_1",
+ "8.1GB"
+ ],
+ [
+ "10.7b-text-v1-q5_K_M",
+ "7.6GB"
+ ],
+ [
+ "10.7b-text-v1-q5_K_S",
+ "7.4GB"
+ ],
+ [
+ "10.7b-text-v1-q6_K",
+ "8.8GB"
+ ],
+ [
+ "10.7b-text-v1-q8_0",
+ "11GB"
+ ]
+ ],
+ "image": false,
+ "author": "Upstage"
},
"wizardlm": {
"url": "https://ollama.com/library/wizardlm",
@@ -16635,6 +16723,74 @@
"image": false,
"author": "Eric Hartford"
},
+ "dolphin-phi": {
+ "url": "https://ollama.com/library/dolphin-phi",
+ "description": "2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.",
+ "tags": [
+ [
+ "latest",
+ "1.6GB"
+ ],
+ [
+ "2.7b",
+ "1.6GB"
+ ],
+ [
+ "2.7b-v2.6",
+ "1.6GB"
+ ],
+ [
+ "2.7b-v2.6-q2_K",
+ "1.2GB"
+ ],
+ [
+ "2.7b-v2.6-q3_K_L",
+ "1.6GB"
+ ],
+ [
+ "2.7b-v2.6-q3_K_M",
+ "1.5GB"
+ ],
+ [
+ "2.7b-v2.6-q3_K_S",
+ "1.3GB"
+ ],
+ [
+ "2.7b-v2.6-q4_0",
+ "1.6GB"
+ ],
+ [
+ "2.7b-v2.6-q4_K_M",
+ "1.8GB"
+ ],
+ [
+ "2.7b-v2.6-q4_K_S",
+ "1.6GB"
+ ],
+ [
+ "2.7b-v2.6-q5_0",
+ "1.9GB"
+ ],
+ [
+ "2.7b-v2.6-q5_K_M",
+ "2.1GB"
+ ],
+ [
+ "2.7b-v2.6-q5_K_S",
+ "1.9GB"
+ ],
+ [
+ "2.7b-v2.6-q6_K",
+ "2.3GB"
+ ],
+ [
+ "2.7b-v2.6-q8_0",
+ "3.0GB"
+ ]
+ ],
+ "image": false,
+ "author": "Eric Hartford"
+ },
"stable-beluga": {
"url": "https://ollama.com/library/stable-beluga",
"description": "Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.",
@@ -16839,6 +16995,86 @@
"image": false,
"author": "Stability AI"
},
+ "moondream": {
+ "url": "https://ollama.com/library/moondream",
+ "description": "moondream2 is a small vision language model designed to run efficiently on edge devices.",
+ "tags": [
+ [
+ "latest",
+ "1.7GB"
+ ],
+ [
+ "1.8b",
+ "1.7GB"
+ ],
+ [
+ "v2",
+ "1.7GB"
+ ],
+ [
+ "1.8b-v2-fp16",
+ "3.7GB"
+ ],
+ [
+ "1.8b-v2-q2_K",
+ "1.5GB"
+ ],
+ [
+ "1.8b-v2-q3_K_L",
+ "1.7GB"
+ ],
+ [
+ "1.8b-v2-q3_K_M",
+ "1.7GB"
+ ],
+ [
+ "1.8b-v2-q3_K_S",
+ "1.6GB"
+ ],
+ [
+ "1.8b-v2-q4_0",
+ "1.7GB"
+ ],
+ [
+ "1.8b-v2-q4_1",
+ "1.8GB"
+ ],
+ [
+ "1.8b-v2-q4_K_M",
+ "1.8GB"
+ ],
+ [
+ "1.8b-v2-q4_K_S",
+ "1.7GB"
+ ],
+ [
+ "1.8b-v2-q5_0",
+ "1.9GB"
+ ],
+ [
+ "1.8b-v2-q5_1",
+ "2.0GB"
+ ],
+ [
+ "1.8b-v2-q5_K_M",
+ "2.0GB"
+ ],
+ [
+ "1.8b-v2-q5_K_S",
+ "1.9GB"
+ ],
+ [
+ "1.8b-v2-q6_K",
+ "2.1GB"
+ ],
+ [
+ "1.8b-v2-q8_0",
+ "2.4GB"
+ ]
+ ],
+ "image": true,
+ "author": "Vikhyatk"
+ },
"bakllava": {
"url": "https://ollama.com/library/bakllava",
"description": "BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.",
@@ -16915,30 +17151,6 @@
"image": true,
"author": "Skunkworks AI"
},
- "llava-llama3": {
- "url": "https://ollama.com/library/llava-llama3",
- "description": "A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.",
- "tags": [
- [
- "latest",
- "5.5GB"
- ],
- [
- "8b",
- "5.5GB"
- ],
- [
- "8b-v1.1-fp16",
- "17GB"
- ],
- [
- "8b-v1.1-q4_0",
- "5.5GB"
- ]
- ],
- "image": true,
- "author": "Xtuner"
- },
"wizardlm-uncensored": {
"url": "https://ollama.com/library/wizardlm-uncensored",
"description": "Uncensored version of Wizard LM model",
@@ -17019,6 +17231,78 @@
"image": false,
"author": "TheBloke AI"
},
+ "snowflake-arctic-embed": {
+ "url": "https://ollama.com/library/snowflake-arctic-embed",
+ "description": "A suite of text embedding models by Snowflake, optimized for performance.",
+ "tags": [
+ [
+ "latest",
+ "669MB"
+ ],
+ [
+ "335m",
+ "669MB"
+ ],
+ [
+ "137m",
+ "274MB"
+ ],
+ [
+ "110m",
+ "219MB"
+ ],
+ [
+ "33m",
+ "67MB"
+ ],
+ [
+ "22m",
+ "46MB"
+ ],
+ [
+ "l",
+ "669MB"
+ ],
+ [
+ "m",
+ "219MB"
+ ],
+ [
+ "s",
+ "67MB"
+ ],
+ [
+ "xs",
+ "46MB"
+ ],
+ [
+ "335m-l-fp16",
+ "669MB"
+ ],
+ [
+ "137m-m-long-fp16",
+ "274MB"
+ ],
+ [
+ "110m-m-fp16",
+ "219MB"
+ ],
+ [
+ "33m-s-fp16",
+ "67MB"
+ ],
+ [
+ "22m-xs-fp16",
+ "46MB"
+ ],
+ [
+ "m-long",
+ "274MB"
+ ]
+ ],
+ "image": false,
+ "author": "Snowflake"
+ },
"medllama2": {
"url": "https://ollama.com/library/medllama2",
"description": "Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.",
@@ -17095,86 +17379,6 @@
"image": false,
"author": "Siraj Raval"
},
- "nous-hermes2-mixtral": {
- "url": "https://ollama.com/library/nous-hermes2-mixtral",
- "description": "The Nous Hermes 2 model from Nous Research, now trained over Mixtral.",
- "tags": [
- [
- "latest",
- "26GB"
- ],
- [
- "8x7b",
- "26GB"
- ],
- [
- "dpo",
- "26GB"
- ],
- [
- "8x7b-dpo-fp16",
- "93GB"
- ],
- [
- "8x7b-dpo-q2_K",
- "16GB"
- ],
- [
- "8x7b-dpo-q3_K_L",
- "20GB"
- ],
- [
- "8x7b-dpo-q3_K_M",
- "20GB"
- ],
- [
- "8x7b-dpo-q3_K_S",
- "20GB"
- ],
- [
- "8x7b-dpo-q4_0",
- "26GB"
- ],
- [
- "8x7b-dpo-q4_1",
- "29GB"
- ],
- [
- "8x7b-dpo-q4_K_M",
- "26GB"
- ],
- [
- "8x7b-dpo-q4_K_S",
- "26GB"
- ],
- [
- "8x7b-dpo-q5_0",
- "32GB"
- ],
- [
- "8x7b-dpo-q5_1",
- "35GB"
- ],
- [
- "8x7b-dpo-q5_K_M",
- "32GB"
- ],
- [
- "8x7b-dpo-q5_K_S",
- "32GB"
- ],
- [
- "8x7b-dpo-q6_K",
- "38GB"
- ],
- [
- "8x7b-dpo-q8_0",
- "50GB"
- ]
- ],
- "image": false,
- "author": "Nous Research"
- },
"yarn-mistral": {
"url": "https://ollama.com/library/yarn-mistral",
"description": "An extension of Mistral to support context windows of 64K or 128K.",
@@ -17315,77 +17519,85 @@
"image": false,
"author": "Nous Research"
},
- "snowflake-arctic-embed": {
- "url": "https://ollama.com/library/snowflake-arctic-embed",
- "description": "A suite of text embedding models by Snowflake, optimized for performance.",
+ "nous-hermes2-mixtral": {
+ "url": "https://ollama.com/library/nous-hermes2-mixtral",
+ "description": "The Nous Hermes 2 model from Nous Research, now trained over Mixtral.",
"tags": [
[
"latest",
- "669MB"
+ "26GB"
],
[
- "335m",
- "669MB"
+ "8x7b",
+ "26GB"
],
[
- "137m",
- "274MB"
+ "dpo",
+ "26GB"
],
[
- "110m",
- "219MB"
+ "8x7b-dpo-fp16",
+ "93GB"
],
[
- "33m",
- "67MB"
+ "8x7b-dpo-q2_K",
+ "16GB"
],
[
- "22m",
- "46MB"
+ "8x7b-dpo-q3_K_L",
+ "20GB"
],
[
- "l",
- "669MB"
+ "8x7b-dpo-q3_K_M",
+ "20GB"
],
[
- "m",
- "219MB"
+ "8x7b-dpo-q3_K_S",
+ "20GB"
],
[
- "s",
- "67MB"
+ "8x7b-dpo-q4_0",
+ "26GB"
],
[
- "xs",
- "46MB"
+ "8x7b-dpo-q4_1",
+ "29GB"
],
[
- "335m-l-fp16",
- "669MB"
+ "8x7b-dpo-q4_K_M",
+ "26GB"
],
[
- "137m-m-long-fp16",
- "274MB"
+ "8x7b-dpo-q4_K_S",
+ "26GB"
],
[
- "110m-m-fp16",
- "219MB"
+ "8x7b-dpo-q5_0",
+ "32GB"
],
[
- "33m-s-fp16",
- "67MB"
+ "8x7b-dpo-q5_1",
+ "35GB"
],
[
- "22m-xs-fp16",
- "46MB"
+ "8x7b-dpo-q5_K_M",
+ "32GB"
],
[
- "m-long",
- "274MB"
+ "8x7b-dpo-q5_K_S",
+ "32GB"
+ ],
+ [
+ "8x7b-dpo-q6_K",
+ "38GB"
+ ],
+ [
+ "8x7b-dpo-q8_0",
+ "50GB"
]
],
"image": false,
- "author": "Snowflake"
+ "author": "Nous Research"
},
"llama-pro": {
"url": "https://ollama.com/library/llama-pro",
@@ -17527,562 +17739,6 @@
"image": false,
"author": "Tencent"
},
- "codeup": {
- "url": "https://ollama.com/library/codeup",
- "description": "Great code generation model based on Llama2.",
- "tags": [
- [
- "latest",
- "7.4GB"
- ],
- [
- "13b",
- "7.4GB"
- ],
- [
- "13b-llama2",
- "7.4GB"
- ],
- [
- "13b-llama2-chat",
- "7.4GB"
- ],
- [
- "13b-llama2-chat-fp16",
- "26GB"
- ],
- [
- "13b-llama2-chat-q2_K",
- "5.4GB"
- ],
- [
- "13b-llama2-chat-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-llama2-chat-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-llama2-chat-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-llama2-chat-q4_0",
- "7.4GB"
- ],
- [
- "13b-llama2-chat-q4_1",
- "8.2GB"
- ],
- [
- "13b-llama2-chat-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-llama2-chat-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-llama2-chat-q5_0",
- "9.0GB"
- ],
- [
- "13b-llama2-chat-q5_1",
- "9.8GB"
- ],
- [
- "13b-llama2-chat-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-llama2-chat-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-llama2-chat-q6_K",
- "11GB"
- ],
- [
- "13b-llama2-chat-q8_0",
- "14GB"
- ]
- ],
- "image": false,
- "author": "DeepSE"
- },
- "meditron": {
- "url": "https://ollama.com/library/meditron",
- "description": "Open-source medical large language model adapted from Llama 2 to the medical domain.",
- "tags": [
- [
- "latest",
- "3.8GB"
- ],
- [
- "70b",
- "39GB"
- ],
- [
- "7b",
- "3.8GB"
- ],
- [
- "70b-q4_0",
- "39GB"
- ],
- [
- "70b-q4_1",
- "43GB"
- ],
- [
- "70b-q4_K_S",
- "39GB"
- ],
- [
- "70b-q5_1",
- "52GB"
- ],
- [
- "7b-fp16",
- "13GB"
- ],
- [
- "7b-q2_K",
- "2.8GB"
- ],
- [
- "7b-q3_K_L",
- "3.6GB"
- ],
- [
- "7b-q3_K_M",
- "3.3GB"
- ],
- [
- "7b-q3_K_S",
- "2.9GB"
- ],
- [
- "7b-q4_0",
- "3.8GB"
- ],
- [
- "7b-q4_1",
- "4.2GB"
- ],
- [
- "7b-q4_K_M",
- "4.1GB"
- ],
- [
- "7b-q4_K_S",
- "3.9GB"
- ],
- [
- "7b-q5_0",
- "4.7GB"
- ],
- [
- "7b-q5_1",
- "5.1GB"
- ],
- [
- "7b-q5_K_M",
- "4.8GB"
- ],
- [
- "7b-q5_K_S",
- "4.7GB"
- ],
- [
- "7b-q6_K",
- "5.5GB"
- ],
- [
- "7b-q8_0",
- "7.2GB"
- ]
- ],
- "image": false,
- "author": "EPFL LLM Team"
- },
- "moondream": {
- "url": "https://ollama.com/library/moondream",
- "description": "moondream2 is a small vision language model designed to run efficiently on edge devices.",
- "tags": [
- [
- "latest",
- "1.7GB"
- ],
- [
- "1.8b",
- "1.7GB"
- ],
- [
- "v2",
- "1.7GB"
- ],
- [
- "1.8b-v2-fp16",
- "3.7GB"
- ],
- [
- "1.8b-v2-q2_K",
- "1.5GB"
- ],
- [
- "1.8b-v2-q3_K_L",
- "1.7GB"
- ],
- [
- "1.8b-v2-q3_K_M",
- "1.7GB"
- ],
- [
- "1.8b-v2-q3_K_S",
- "1.6GB"
- ],
- [
- "1.8b-v2-q4_0",
- "1.7GB"
- ],
- [
- "1.8b-v2-q4_1",
- "1.8GB"
- ],
- [
- "1.8b-v2-q4_K_M",
- "1.8GB"
- ],
- [
- "1.8b-v2-q4_K_S",
- "1.7GB"
- ],
- [
- "1.8b-v2-q5_0",
- "1.9GB"
- ],
- [
- "1.8b-v2-q5_1",
- "2.0GB"
- ],
- [
- "1.8b-v2-q5_K_M",
- "2.0GB"
- ],
- [
- "1.8b-v2-q5_K_S",
- "1.9GB"
- ],
- [
- "1.8b-v2-q6_K",
- "2.1GB"
- ],
- [
- "1.8b-v2-q8_0",
- "2.4GB"
- ]
- ],
- "image": true,
- "author": "Vikhyatk"
- },
- "everythinglm": {
- "url": "https://ollama.com/library/everythinglm",
- "description": "Uncensored Llama2 based model with support for a 16K context window.",
- "tags": [
- [
- "latest",
- "7.4GB"
- ],
- [
- "13b",
- "7.4GB"
- ],
- [
- "13b-16k",
- "7.4GB"
- ],
- [
- "13b-16k-fp16",
- "26GB"
- ],
- [
- "13b-16k-q2_K",
- "5.4GB"
- ],
- [
- "13b-16k-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-16k-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-16k-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-16k-q4_0",
- "7.4GB"
- ],
- [
- "13b-16k-q4_1",
- "8.2GB"
- ],
- [
- "13b-16k-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-16k-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-16k-q5_0",
- "9.0GB"
- ],
- [
- "13b-16k-q5_1",
- "9.8GB"
- ],
- [
- "13b-16k-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-16k-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-16k-q6_K",
- "11GB"
- ],
- [
- "13b-16k-q8_0",
- "14GB"
- ]
- ],
- "image": false,
- "author": "Totally Not An LLM"
- },
- "nexusraven": {
- "url": "https://ollama.com/library/nexusraven",
- "description": "Nexus Raven is a 13B instruction tuned model for function calling tasks.",
- "tags": [
- [
- "latest",
- "7.4GB"
- ],
- [
- "13b",
- "7.4GB"
- ],
- [
- "13b-v2-fp16",
- "26GB"
- ],
- [
- "13b-v2-q2_K",
- "5.4GB"
- ],
- [
- "13b-v2-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-v2-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-v2-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-v2-q4_0",
- "7.4GB"
- ],
- [
- "13b-v2-q4_1",
- "8.2GB"
- ],
- [
- "13b-v2-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-v2-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-v2-q5_0",
- "9.0GB"
- ],
- [
- "13b-v2-q5_1",
- "9.8GB"
- ],
- [
- "13b-v2-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-v2-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-v2-q6_K",
- "11GB"
- ],
- [
- "13b-v2-q8_0",
- "14GB"
- ],
- [
- "13b-fp16",
- "26GB"
- ],
- [
- "13b-q2_K",
- "5.4GB"
- ],
- [
- "13b-q3_K_L",
- "6.9GB"
- ],
- [
- "13b-q3_K_M",
- "6.3GB"
- ],
- [
- "13b-q3_K_S",
- "5.7GB"
- ],
- [
- "13b-q4_0",
- "7.4GB"
- ],
- [
- "13b-q4_1",
- "8.2GB"
- ],
- [
- "13b-q4_K_M",
- "7.9GB"
- ],
- [
- "13b-q4_K_S",
- "7.4GB"
- ],
- [
- "13b-q5_0",
- "9.0GB"
- ],
- [
- "13b-q5_1",
- "9.8GB"
- ],
- [
- "13b-q5_K_M",
- "9.2GB"
- ],
- [
- "13b-q5_K_S",
- "9.0GB"
- ],
- [
- "13b-q6_K",
- "11GB"
- ],
- [
- "13b-q8_0",
- "14GB"
- ]
- ],
- "image": false,
- "author": "NexusFlow AI"
- },
- "magicoder": {
- "url": "https://ollama.com/library/magicoder",
- "description": "\ud83c\udfa9 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.",
- "tags": [
- [
- "latest",
- "3.8GB"
- ],
- [
- "7b",
- "3.8GB"
- ],
- [
- "7b-s-cl",
- "3.8GB"
- ],
- [
- "7b-s-cl-fp16",
- "13GB"
- ],
- [
- "7b-s-cl-q2_K",
- "2.8GB"
- ],
- [
- "7b-s-cl-q3_K_L",
- "3.6GB"
- ],
- [
- "7b-s-cl-q3_K_M",
- "3.3GB"
- ],
- [
- "7b-s-cl-q3_K_S",
- "2.9GB"
- ],
- [
- "7b-s-cl-q4_0",
- "3.8GB"
- ],
- [
- "7b-s-cl-q4_1",
- "4.2GB"
- ],
- [
- "7b-s-cl-q4_K_M",
- "4.1GB"
- ],
- [
- "7b-s-cl-q4_K_S",
- "3.9GB"
- ],
- [
- "7b-s-cl-q5_0",
- "4.7GB"
- ],
- [
- "7b-s-cl-q5_1",
- "5.1GB"
- ],
- [
- "7b-s-cl-q5_K_M",
- "4.8GB"
- ],
- [
- "7b-s-cl-q5_K_S",
- "4.7GB"
- ],
- [
- "7b-s-cl-q6_K",
- "5.5GB"
- ],
- [
- "7b-s-cl-q8_0",
- "7.2GB"
- ]
- ],
- "image": false,
- "author": "iSE"
- },
"deepseek-v2": {
"url": "https://ollama.com/library/deepseek-v2",
"description": "A strong, economical, and efficient Mixture-of-Experts language model.",
@@ -18235,6 +17891,506 @@
"image": false,
"author": "DeepSeek Team"
},
+ "meditron": {
+ "url": "https://ollama.com/library/meditron",
+ "description": "Open-source medical large language model adapted from Llama 2 to the medical domain.",
+ "tags": [
+ [
+ "latest",
+ "3.8GB"
+ ],
+ [
+ "70b",
+ "39GB"
+ ],
+ [
+ "7b",
+ "3.8GB"
+ ],
+ [
+ "70b-q4_0",
+ "39GB"
+ ],
+ [
+ "70b-q4_1",
+ "43GB"
+ ],
+ [
+ "70b-q4_K_S",
+ "39GB"
+ ],
+ [
+ "70b-q5_1",
+ "52GB"
+ ],
+ [
+ "7b-fp16",
+ "13GB"
+ ],
+ [
+ "7b-q2_K",
+ "2.8GB"
+ ],
+ [
+ "7b-q3_K_L",
+ "3.6GB"
+ ],
+ [
+ "7b-q3_K_M",
+ "3.3GB"
+ ],
+ [
+ "7b-q3_K_S",
+ "2.9GB"
+ ],
+ [
+ "7b-q4_0",
+ "3.8GB"
+ ],
+ [
+ "7b-q4_1",
+ "4.2GB"
+ ],
+ [
+ "7b-q4_K_M",
+ "4.1GB"
+ ],
+ [
+ "7b-q4_K_S",
+ "3.9GB"
+ ],
+ [
+ "7b-q5_0",
+ "4.7GB"
+ ],
+ [
+ "7b-q5_1",
+ "5.1GB"
+ ],
+ [
+ "7b-q5_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-q5_K_S",
+ "4.7GB"
+ ],
+ [
+ "7b-q6_K",
+ "5.5GB"
+ ],
+ [
+ "7b-q8_0",
+ "7.2GB"
+ ]
+ ],
+ "image": false,
+ "author": "EPFL LLM Team"
+ },
+ "codeup": {
+ "url": "https://ollama.com/library/codeup",
+ "description": "Great code generation model based on Llama2.",
+ "tags": [
+ [
+ "latest",
+ "7.4GB"
+ ],
+ [
+ "13b",
+ "7.4GB"
+ ],
+ [
+ "13b-llama2",
+ "7.4GB"
+ ],
+ [
+ "13b-llama2-chat",
+ "7.4GB"
+ ],
+ [
+ "13b-llama2-chat-fp16",
+ "26GB"
+ ],
+ [
+ "13b-llama2-chat-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-llama2-chat-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-llama2-chat-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-llama2-chat-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-llama2-chat-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-llama2-chat-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-llama2-chat-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-llama2-chat-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-llama2-chat-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-llama2-chat-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-llama2-chat-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-llama2-chat-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-llama2-chat-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-llama2-chat-q8_0",
+ "14GB"
+ ]
+ ],
+ "image": false,
+ "author": "DeepSE"
+ },
+ "nexusraven": {
+ "url": "https://ollama.com/library/nexusraven",
+ "description": "Nexus Raven is a 13B instruction tuned model for function calling tasks.",
+ "tags": [
+ [
+ "latest",
+ "7.4GB"
+ ],
+ [
+ "13b",
+ "7.4GB"
+ ],
+ [
+ "13b-v2-fp16",
+ "26GB"
+ ],
+ [
+ "13b-v2-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-v2-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-v2-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-v2-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-v2-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-v2-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-v2-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-v2-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-v2-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-v2-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-v2-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-v2-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-v2-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-v2-q8_0",
+ "14GB"
+ ],
+ [
+ "13b-fp16",
+ "26GB"
+ ],
+ [
+ "13b-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-q8_0",
+ "14GB"
+ ]
+ ],
+ "image": false,
+ "author": "NexusFlow AI"
+ },
+ "everythinglm": {
+ "url": "https://ollama.com/library/everythinglm",
+ "description": "Uncensored Llama2 based model with support for a 16K context window.",
+ "tags": [
+ [
+ "latest",
+ "7.4GB"
+ ],
+ [
+ "13b",
+ "7.4GB"
+ ],
+ [
+ "13b-16k",
+ "7.4GB"
+ ],
+ [
+ "13b-16k-fp16",
+ "26GB"
+ ],
+ [
+ "13b-16k-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-16k-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-16k-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-16k-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-16k-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-16k-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-16k-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-16k-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-16k-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-16k-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-16k-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-16k-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-16k-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-16k-q8_0",
+ "14GB"
+ ]
+ ],
+ "image": false,
+ "author": "Totally Not An LLM"
+ },
+ "llava-phi3": {
+ "url": "https://ollama.com/library/llava-phi3",
+ "description": "A new small LLaVA model fine-tuned from Phi 3 Mini.",
+ "tags": [
+ [
+ "latest",
+ "2.9GB"
+ ],
+ [
+ "3.8b",
+ "2.9GB"
+ ],
+ [
+ "3.8b-mini-fp16",
+ "8.3GB"
+ ],
+ [
+ "3.8b-mini-q4_0",
+ "2.9GB"
+ ]
+ ],
+ "image": false,
+ "author": "Xtuner"
+ },
+ "magicoder": {
+ "url": "https://ollama.com/library/magicoder",
+ "description": "\ud83c\udfa9 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.",
+ "tags": [
+ [
+ "latest",
+ "3.8GB"
+ ],
+ [
+ "7b",
+ "3.8GB"
+ ],
+ [
+ "7b-s-cl",
+ "3.8GB"
+ ],
+ [
+ "7b-s-cl-fp16",
+ "13GB"
+ ],
+ [
+ "7b-s-cl-q2_K",
+ "2.8GB"
+ ],
+ [
+ "7b-s-cl-q3_K_L",
+ "3.6GB"
+ ],
+ [
+ "7b-s-cl-q3_K_M",
+ "3.3GB"
+ ],
+ [
+ "7b-s-cl-q3_K_S",
+ "2.9GB"
+ ],
+ [
+ "7b-s-cl-q4_0",
+ "3.8GB"
+ ],
+ [
+ "7b-s-cl-q4_1",
+ "4.2GB"
+ ],
+ [
+ "7b-s-cl-q4_K_M",
+ "4.1GB"
+ ],
+ [
+ "7b-s-cl-q4_K_S",
+ "3.9GB"
+ ],
+ [
+ "7b-s-cl-q5_0",
+ "4.7GB"
+ ],
+ [
+ "7b-s-cl-q5_1",
+ "5.1GB"
+ ],
+ [
+ "7b-s-cl-q5_K_M",
+ "4.8GB"
+ ],
+ [
+ "7b-s-cl-q5_K_S",
+ "4.7GB"
+ ],
+ [
+ "7b-s-cl-q6_K",
+ "5.5GB"
+ ],
+ [
+ "7b-s-cl-q8_0",
+ "7.2GB"
+ ]
+ ],
+ "image": false,
+ "author": "iSE"
+ },
"stablelm-zephyr": {
"url": "https://ollama.com/library/stablelm-zephyr",
"description": "A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.",
@@ -18383,30 +18539,6 @@
"image": false,
"author": "Oobabooga"
},
- "llava-phi3": {
- "url": "https://ollama.com/library/llava-phi3",
- "description": "A new small LLaVA model fine-tuned from Phi 3 Mini.",
- "tags": [
- [
- "latest",
- "2.9GB"
- ],
- [
- "3.8b",
- "2.9GB"
- ],
- [
- "3.8b-mini-fp16",
- "8.3GB"
- ],
- [
- "3.8b-mini-q4_0",
- "2.9GB"
- ]
- ],
- "image": false,
- "author": "Xtuner"
- },
"mistrallite": {
"url": "https://ollama.com/library/mistrallite",
"description": "MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.",
@@ -18483,77 +18615,273 @@
"image": false,
"author": "Amazon Web Services"
},
- "wizard-vicuna": {
- "url": "https://ollama.com/library/wizard-vicuna",
- "description": "Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.",
+ "glm4": {
+ "url": "https://ollama.com/library/glm4",
+ "description": "A strong multi-lingual general language model with competitive performance to Llama 3.",
"tags": [
[
"latest",
- "7.4GB"
+ "5.5GB"
],
[
- "13b",
- "7.4GB"
+ "9b",
+ "5.5GB"
],
[
- "13b-fp16",
- "26GB"
+ "9b-chat-fp16",
+ "19GB"
],
[
- "13b-q2_K",
- "5.4GB"
+ "9b-chat-q2_K",
+ "4.0GB"
],
[
- "13b-q3_K_L",
- "6.9GB"
+ "9b-chat-q3_K_L",
+ "5.3GB"
],
[
- "13b-q3_K_M",
+ "9b-chat-q3_K_M",
+ "5.1GB"
+ ],
+ [
+ "9b-chat-q3_K_S",
+ "4.6GB"
+ ],
+ [
+ "9b-chat-q4_0",
+ "5.5GB"
+ ],
+ [
+ "9b-chat-q4_1",
+ "6.0GB"
+ ],
+ [
+ "9b-chat-q4_K_M",
"6.3GB"
],
[
- "13b-q3_K_S",
- "5.7GB"
+ "9b-chat-q4_K_S",
+ "5.8GB"
],
[
- "13b-q4_0",
- "7.4GB"
+ "9b-chat-q5_0",
+ "6.6GB"
],
[
- "13b-q4_1",
- "8.2GB"
+ "9b-chat-q5_1",
+ "7.1GB"
],
[
- "13b-q4_K_M",
- "7.9GB"
+ "9b-chat-q5_K_M",
+ "7.1GB"
],
[
- "13b-q4_K_S",
- "7.4GB"
+ "9b-chat-q5_K_S",
+ "6.7GB"
],
[
- "13b-q5_0",
- "9.0GB"
+ "9b-chat-q6_K",
+ "8.3GB"
],
[
- "13b-q5_1",
- "9.8GB"
+ "9b-chat-q8_0",
+ "10.0GB"
],
[
- "13b-q5_K_M",
- "9.2GB"
+ "9b-text-fp16",
+ "19GB"
],
[
- "13b-q5_K_S",
- "9.0GB"
+ "9b-text-q2_K",
+ "4.0GB"
],
[
- "13b-q6_K",
- "11GB"
+ "9b-text-q3_K_L",
+ "5.3GB"
],
[
- "13b-q8_0",
- "14GB"
+ "9b-text-q3_K_M",
+ "5.1GB"
+ ],
+ [
+ "9b-text-q3_K_S",
+ "4.6GB"
+ ],
+ [
+ "9b-text-q4_0",
+ "5.5GB"
+ ],
+ [
+ "9b-text-q4_1",
+ "6.0GB"
+ ],
+ [
+ "9b-text-q4_K_M",
+ "6.3GB"
+ ],
+ [
+ "9b-text-q4_K_S",
+ "5.8GB"
+ ],
+ [
+ "9b-text-q5_0",
+ "6.6GB"
+ ],
+ [
+ "9b-text-q5_1",
+ "7.1GB"
+ ],
+ [
+ "9b-text-q5_K_M",
+ "7.1GB"
+ ],
+ [
+ "9b-text-q5_K_S",
+ "6.7GB"
+ ],
+ [
+ "9b-text-q6_K",
+ "8.3GB"
+ ],
+ [
+ "9b-text-q8_0",
+ "10.0GB"
+ ]
+ ],
+ "image": false,
+ "author": "THUDM"
+ },
+ "wizard-vicuna": {
+ "url": "https://ollama.com/library/wizard-vicuna",
+ "description": "A strong multi-lingual general language model with competitive performance to Llama 3.",
+ "tags": [
+ [
+ "latest",
+ "5.5GB"
+ ],
+ [
+ "9b",
+ "5.5GB"
+ ],
+ [
+ "9b-chat-fp16",
+ "19GB"
+ ],
+ [
+ "9b-chat-q2_K",
+ "4.0GB"
+ ],
+ [
+ "9b-chat-q3_K_L",
+ "5.3GB"
+ ],
+ [
+ "9b-chat-q3_K_M",
+ "5.1GB"
+ ],
+ [
+ "9b-chat-q3_K_S",
+ "4.6GB"
+ ],
+ [
+ "9b-chat-q4_0",
+ "5.5GB"
+ ],
+ [
+ "9b-chat-q4_1",
+ "6.0GB"
+ ],
+ [
+ "9b-chat-q4_K_M",
+ "6.3GB"
+ ],
+ [
+ "9b-chat-q4_K_S",
+ "5.8GB"
+ ],
+ [
+ "9b-chat-q5_0",
+ "6.6GB"
+ ],
+ [
+ "9b-chat-q5_1",
+ "7.1GB"
+ ],
+ [
+ "9b-chat-q5_K_M",
+ "7.1GB"
+ ],
+ [
+ "9b-chat-q5_K_S",
+ "6.7GB"
+ ],
+ [
+ "9b-chat-q6_K",
+ "8.3GB"
+ ],
+ [
+ "9b-chat-q8_0",
+ "10.0GB"
+ ],
+ [
+ "9b-text-fp16",
+ "19GB"
+ ],
+ [
+ "9b-text-q2_K",
+ "4.0GB"
+ ],
+ [
+ "9b-text-q3_K_L",
+ "5.3GB"
+ ],
+ [
+ "9b-text-q3_K_M",
+ "5.1GB"
+ ],
+ [
+ "9b-text-q3_K_S",
+ "4.6GB"
+ ],
+ [
+ "9b-text-q4_0",
+ "5.5GB"
+ ],
+ [
+ "9b-text-q4_1",
+ "6.0GB"
+ ],
+ [
+ "9b-text-q4_K_M",
+ "6.3GB"
+ ],
+ [
+ "9b-text-q4_K_S",
+ "5.8GB"
+ ],
+ [
+ "9b-text-q5_0",
+ "6.6GB"
+ ],
+ [
+ "9b-text-q5_1",
+ "7.1GB"
+ ],
+ [
+ "9b-text-q5_K_M",
+ "7.1GB"
+ ],
+ [
+ "9b-text-q5_K_S",
+ "6.7GB"
+ ],
+ [
+ "9b-text-q6_K",
+ "8.3GB"
+ ],
+ [
+ "9b-text-q8_0",
+ "10.0GB"
]
],
"image": false,
@@ -18635,78 +18963,6 @@
"image": false,
"author": "MotherDuck, Numbers Station"
},
- "goliath": {
- "url": "https://ollama.com/library/goliath",
- "description": "A language model created by combining two fine-tuned Llama 2 70B models into one.",
- "tags": [
- [
- "latest",
- "66GB"
- ],
- [
- "120b-fp16",
- "236GB"
- ],
- [
- "120b-q2_K",
- "50GB"
- ],
- [
- "120b-q3_K_L",
- "62GB"
- ],
- [
- "120b-q3_K_M",
- "56GB"
- ],
- [
- "120b-q3_K_S",
- "51GB"
- ],
- [
- "120b-q4_0",
- "66GB"
- ],
- [
- "120b-q4_1",
- "74GB"
- ],
- [
- "120b-q4_K_M",
- "71GB"
- ],
- [
- "120b-q4_K_S",
- "66GB"
- ],
- [
- "120b-q5_0",
- "81GB"
- ],
- [
- "120b-q5_1",
- "88GB"
- ],
- [
- "120b-q5_K_M",
- "83GB"
- ],
- [
- "120b-q5_K_S",
- "81GB"
- ],
- [
- "120b-q6_K",
- "97GB"
- ],
- [
- "120b-q8_0",
- "125GB"
- ]
- ],
- "image": false,
- "author": "Alpindale"
- },
"megadolphin": {
"url": "https://ollama.com/library/megadolphin",
"description": "MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.",
@@ -18791,81 +19047,77 @@
"image": false,
"author": "Cognitive Computations"
},
- "open-orca-platypus2": {
- "url": "https://ollama.com/library/open-orca-platypus2",
- "description": "Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.",
+ "goliath": {
+ "url": "https://ollama.com/library/goliath",
+ "description": "A language model created by combining two fine-tuned Llama 2 70B models into one.",
"tags": [
[
"latest",
- "7.4GB"
+ "66GB"
],
[
- "13b",
- "7.4GB"
+ "120b-q4_0",
+ "66GB"
],
[
- "13b-fp16",
- "26GB"
+ "120b-fp16",
+ "236GB"
],
[
- "13b-q2_K",
- "5.4GB"
+ "120b-q2_K",
+ "50GB"
],
[
- "13b-q3_K_L",
- "6.9GB"
+ "120b-q3_K_L",
+ "62GB"
],
[
- "13b-q3_K_M",
- "6.3GB"
+ "120b-q3_K_M",
+ "56GB"
],
[
- "13b-q3_K_S",
- "5.7GB"
+ "120b-q3_K_S",
+ "51GB"
],
[
- "13b-q4_0",
- "7.4GB"
+ "120b-q4_1",
+ "74GB"
],
[
- "13b-q4_1",
- "8.2GB"
+ "120b-q4_K_M",
+ "71GB"
],
[
- "13b-q4_K_M",
- "7.9GB"
+ "120b-q4_K_S",
+ "66GB"
],
[
- "13b-q4_K_S",
- "7.4GB"
+ "120b-q5_0",
+ "81GB"
],
[
- "13b-q5_0",
- "9.0GB"
+ "120b-q5_1",
+ "88GB"
],
[
- "13b-q5_1",
- "9.8GB"
+ "120b-q5_K_M",
+ "83GB"
],
[
- "13b-q5_K_M",
- "9.2GB"
+ "120b-q5_K_S",
+ "81GB"
],
[
- "13b-q5_K_S",
- "9.0GB"
+ "120b-q6_K",
+ "97GB"
],
[
- "13b-q6_K",
- "11GB"
- ],
- [
- "13b-q8_0",
- "14GB"
+ "120b-q8_0",
+ "125GB"
]
],
"image": false,
- "author": "Open Orca"
+ "author": "Alpindale"
},
"notux": {
"url": "https://ollama.com/library/notux",
@@ -18947,6 +19199,158 @@
"image": false,
"author": "Argilla"
},
+ "open-orca-platypus2": {
+ "url": "https://ollama.com/library/open-orca-platypus2",
+ "description": "Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.",
+ "tags": [
+ [
+ "latest",
+ "7.4GB"
+ ],
+ [
+ "13b",
+ "7.4GB"
+ ],
+ [
+ "13b-fp16",
+ "26GB"
+ ],
+ [
+ "13b-q2_K",
+ "5.4GB"
+ ],
+ [
+ "13b-q3_K_L",
+ "6.9GB"
+ ],
+ [
+ "13b-q3_K_M",
+ "6.3GB"
+ ],
+ [
+ "13b-q3_K_S",
+ "5.7GB"
+ ],
+ [
+ "13b-q4_0",
+ "7.4GB"
+ ],
+ [
+ "13b-q4_1",
+ "8.2GB"
+ ],
+ [
+ "13b-q4_K_M",
+ "7.9GB"
+ ],
+ [
+ "13b-q4_K_S",
+ "7.4GB"
+ ],
+ [
+ "13b-q5_0",
+ "9.0GB"
+ ],
+ [
+ "13b-q5_1",
+ "9.8GB"
+ ],
+ [
+ "13b-q5_K_M",
+ "9.2GB"
+ ],
+ [
+ "13b-q5_K_S",
+ "9.0GB"
+ ],
+ [
+ "13b-q6_K",
+ "11GB"
+ ],
+ [
+ "13b-q8_0",
+ "14GB"
+ ]
+ ],
+ "image": false,
+ "author": "Open Orca"
+ },
+ "falcon2": {
+ "url": "https://ollama.com/library/falcon2",
+ "description": "Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.",
+ "tags": [
+ [
+ "latest",
+ "6.4GB"
+ ],
+ [
+ "11b",
+ "6.4GB"
+ ],
+ [
+ "11b-fp16",
+ "22GB"
+ ],
+ [
+ "11b-q2_K",
+ "4.3GB"
+ ],
+ [
+ "11b-q3_K_L",
+ "5.8GB"
+ ],
+ [
+ "11b-q3_K_M",
+ "5.4GB"
+ ],
+ [
+ "11b-q3_K_S",
+ "4.9GB"
+ ],
+ [
+ "11b-q4_0",
+ "6.4GB"
+ ],
+ [
+ "11b-q4_1",
+ "7.1GB"
+ ],
+ [
+ "11b-q4_K_M",
+ "6.8GB"
+ ],
+ [
+ "11b-q4_K_S",
+ "6.4GB"
+ ],
+ [
+ "11b-q5_0",
+ "7.7GB"
+ ],
+ [
+ "11b-q5_1",
+ "8.4GB"
+ ],
+ [
+ "11b-q5_K_M",
+ "8.2GB"
+ ],
+ [
+ "11b-q5_K_S",
+ "7.7GB"
+ ],
+ [
+ "11b-q6_K",
+ "9.2GB"
+ ],
+ [
+ "11b-q8_0",
+ "12GB"
+ ]
+ ],
+ "image": false,
+ "author": "Technology Innovation Institute"
+ },
"notus": {
"url": "https://ollama.com/library/notus",
"description": "A 7B chat model fine-tuned with high-quality data and based on Zephyr.",
@@ -19063,81 +19467,81 @@
"image": false,
"author": "Databricks"
},
- "falcon2": {
- "url": "https://ollama.com/library/falcon2",
- "description": "Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.",
+ "codegeex4": {
+ "url": "https://ollama.com/library/codegeex4",
+ "description": "A versatile model for AI software development scenarios, including code completion.",
"tags": [
[
"latest",
- "6.4GB"
+ "5.5GB"
],
[
- "11b",
- "6.4GB"
+ "9b",
+ "5.5GB"
],
[
- "11b-fp16",
- "22GB"
+ "9b-all-fp16",
+ "19GB"
],
[
- "11b-q2_K",
- "4.3GB"
+ "9b-all-q2_K",
+ "4.0GB"
],
[
- "11b-q3_K_L",
+ "9b-all-q3_K_L",
+ "5.3GB"
+ ],
+ [
+ "9b-all-q3_K_M",
+ "5.1GB"
+ ],
+ [
+ "9b-all-q3_K_S",
+ "4.6GB"
+ ],
+ [
+ "9b-all-q4_0",
+ "5.5GB"
+ ],
+ [
+ "9b-all-q4_1",
+ "6.0GB"
+ ],
+ [
+ "9b-all-q4_K_M",
+ "6.3GB"
+ ],
+ [
+ "9b-all-q4_K_S",
"5.8GB"
],
[
- "11b-q3_K_M",
- "5.4GB"
+ "9b-all-q5_0",
+ "6.6GB"
],
[
- "11b-q3_K_S",
- "4.9GB"
- ],
- [
- "11b-q4_0",
- "6.4GB"
- ],
- [
- "11b-q4_1",
+ "9b-all-q5_1",
"7.1GB"
],
[
- "11b-q4_K_M",
- "6.8GB"
+ "9b-all-q5_K_M",
+ "7.1GB"
],
[
- "11b-q4_K_S",
- "6.4GB"
+ "9b-all-q5_K_S",
+ "6.7GB"
],
[
- "11b-q5_0",
- "7.7GB"
+ "9b-all-q6_K",
+ "8.3GB"
],
[
- "11b-q5_1",
- "8.4GB"
- ],
- [
- "11b-q5_K_M",
- "8.2GB"
- ],
- [
- "11b-q5_K_S",
- "7.7GB"
- ],
- [
- "11b-q6_K",
- "9.2GB"
- ],
- [
- "11b-q8_0",
- "12GB"
+ "9b-all-q8_0",
+ "10.0GB"
]
],
"image": false,
- "author": "Technology Innovation Institute"
+ "author": "THUDM"
},
"alfred": {
"url": "https://ollama.com/library/alfred",
@@ -19174,5 +19578,525 @@
],
"image": false,
"author": "LightOn AI"
+ },
+ "internlm2": {
+ "url": "https://ollama.com/library/internlm2",
+ "description": "InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.",
+ "tags": [
+ [
+ "latest",
+ "4.5GB"
+ ],
+ [
+ "7b",
+ "4.5GB"
+ ],
+ [
+ "7b-chat-v2.5-fp16",
+ "15GB"
+ ],
+ [
+ "7b-chat-v2.5-q2_K",
+ "3.0GB"
+ ],
+ [
+ "7b-chat-v2.5-q3_K_L",
+ "4.1GB"
+ ],
+ [
+ "7b-chat-v2.5-q3_K_M",
+ "3.8GB"
+ ],
+ [
+ "7b-chat-v2.5-q3_K_S",
+ "3.5GB"
+ ],
+ [
+ "7b-chat-v2.5-q4_0",
+ "4.5GB"
+ ],
+ [
+ "7b-chat-v2.5-q4_1",
+ "4.9GB"
+ ],
+ [
+ "7b-chat-v2.5-q4_K_M",
+ "4.7GB"
+ ],
+ [
+ "7b-chat-v2.5-q4_K_S",
+ "4.5GB"
+ ],
+ [
+ "7b-chat-v2.5-q5_0",
+ "5.4GB"
+ ],
+ [
+ "7b-chat-v2.5-q5_1",
+ "5.8GB"
+ ],
+ [
+ "7b-chat-v2.5-q5_K_M",
+ "5.5GB"
+ ],
+ [
+ "7b-chat-v2.5-q5_K_S",
+ "5.4GB"
+ ],
+ [
+ "7b-chat-v2.5-q6_K",
+ "6.4GB"
+ ],
+ [
+ "7b-chat-v2.5-q8_0",
+ "8.2GB"
+ ]
+ ],
+ "image": false,
+ "author": "InternLM"
+ },
+ "llama3-groq-tool-use": {
+ "url": "https://ollama.com/library/llama3-groq-tool-use",
+ "description": "A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.",
+ "tags": [
+ [
+ "latest",
+ "4.7GB"
+ ],
+ [
+ "70b",
+ "40GB"
+ ],
+ [
+ "8b",
+ "4.7GB"
+ ],
+ [
+ "70b-fp16",
+ "141GB"
+ ],
+ [
+ "70b-q2_K",
+ "26GB"
+ ],
+ [
+ "70b-q3_K_L",
+ "37GB"
+ ],
+ [
+ "70b-q3_K_M",
+ "34GB"
+ ],
+ [
+ "70b-q3_K_S",
+ "31GB"
+ ],
+ [
+ "70b-q4_0",
+ "40GB"
+ ],
+ [
+ "70b-q4_1",
+ "44GB"
+ ],
+ [
+ "70b-q4_K_M",
+ "43GB"
+ ],
+ [
+ "70b-q4_K_S",
+ "40GB"
+ ],
+ [
+ "70b-q5_0",
+ "49GB"
+ ],
+ [
+ "70b-q5_1",
+ "53GB"
+ ],
+ [
+ "70b-q5_K_M",
+ "50GB"
+ ],
+ [
+ "70b-q5_K_S",
+ "49GB"
+ ],
+ [
+ "70b-q6_K",
+ "58GB"
+ ],
+ [
+ "70b-q8_0",
+ "75GB"
+ ],
+ [
+ "8b-fp16",
+ "16GB"
+ ],
+ [
+ "8b-q2_K",
+ "3.2GB"
+ ],
+ [
+ "8b-q3_K_L",
+ "4.3GB"
+ ],
+ [
+ "8b-q3_K_M",
+ "4.0GB"
+ ],
+ [
+ "8b-q3_K_S",
+ "3.7GB"
+ ],
+ [
+ "8b-q4_0",
+ "4.7GB"
+ ],
+ [
+ "8b-q4_1",
+ "5.1GB"
+ ],
+ [
+ "8b-q4_K_M",
+ "4.9GB"
+ ],
+ [
+ "8b-q4_K_S",
+ "4.7GB"
+ ],
+ [
+ "8b-q5_0",
+ "5.6GB"
+ ],
+ [
+ "8b-q5_1",
+ "6.1GB"
+ ],
+ [
+ "8b-q5_K_M",
+ "5.7GB"
+ ],
+ [
+ "8b-q5_K_S",
+ "5.6GB"
+ ],
+ [
+ "8b-q6_K",
+ "6.6GB"
+ ],
+ [
+ "8b-q8_0",
+ "8.5GB"
+ ]
+ ],
+ "image": false,
+ "author": "Groq Inc"
+ },
+ "mathstral": {
+ "url": "https://ollama.com/library/mathstral",
+ "description": "Math\u03a3tral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.",
+ "tags": [
+ [
+ "latest",
+ "4.1GB"
+ ],
+ [
+ "7b",
+ "4.1GB"
+ ],
+ [
+ "7b-v0.1-fp16",
+ "14GB"
+ ],
+ [
+ "7b-v0.1-q2_K",
+ "2.7GB"
+ ],
+ [
+ "7b-v0.1-q3_K_L",
+ "3.8GB"
+ ],
+ [
+ "7b-v0.1-q3_K_M",
+ "3.5GB"
+ ],
+ [
+ "7b-v0.1-q3_K_S",
+ "3.2GB"
+ ],
+ [
+ "7b-v0.1-q4_0",
+ "4.1GB"
+ ],
+ [
+ "7b-v0.1-q4_1",
+ "4.6GB"
+ ],
+ [
+ "7b-v0.1-q4_K_M",
+ "4.4GB"
+ ],
+ [
+ "7b-v0.1-q4_K_S",
+ "4.1GB"
+ ],
+ [
+ "7b-v0.1-q5_0",
+ "5.0GB"
+ ],
+ [
+ "7b-v0.1-q5_1",
+ "5.4GB"
+ ],
+ [
+ "7b-v0.1-q5_K_M",
+ "5.1GB"
+ ],
+ [
+ "7b-v0.1-q5_K_S",
+ "5.0GB"
+ ],
+ [
+ "7b-v0.1-q6_K",
+ "5.9GB"
+ ],
+ [
+ "7b-v0.1-q8_0",
+ "7.7GB"
+ ]
+ ],
+ "image": false,
+ "author": "Mistral AI"
+ },
+ "mistral-nemo": {
+ "url": "https://ollama.com/library/mistral-nemo",
+ "description": "A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.",
+ "tags": [
+ [
+ "latest",
+ "7.1GB"
+ ],
+ [
+ "12b",
+ "7.1GB"
+ ],
+ [
+ "12b-instruct-2407-fp16",
+ "25GB"
+ ],
+ [
+ "12b-instruct-2407-q2_K",
+ "4.8GB"
+ ],
+ [
+ "12b-instruct-2407-q3_K_L",
+ "6.6GB"
+ ],
+ [
+ "12b-instruct-2407-q3_K_M",
+ "6.1GB"
+ ],
+ [
+ "12b-instruct-2407-q3_K_S",
+ "5.5GB"
+ ],
+ [
+ "12b-instruct-2407-q4_0",
+ "7.1GB"
+ ],
+ [
+ "12b-instruct-2407-q4_1",
+ "7.8GB"
+ ],
+ [
+ "12b-instruct-2407-q4_K_M",
+ "7.5GB"
+ ],
+ [
+ "12b-instruct-2407-q4_K_S",
+ "7.1GB"
+ ],
+ [
+ "12b-instruct-2407-q5_0",
+ "8.5GB"
+ ],
+ [
+ "12b-instruct-2407-q5_1",
+ "9.2GB"
+ ],
+ [
+ "12b-instruct-2407-q5_K_M",
+ "8.7GB"
+ ],
+ [
+ "12b-instruct-2407-q5_K_S",
+ "8.5GB"
+ ],
+ [
+ "12b-instruct-2407-q6_K",
+ "10GB"
+ ],
+ [
+ "12b-instruct-2407-q8_0",
+ "13GB"
+ ]
+ ],
+ "image": false,
+ "author": "Mistral AI"
+ },
+ "firefunction-v2": {
+ "url": "https://ollama.com/library/firefunction-v2",
+ "description": "An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.",
+ "tags": [
+ [
+ "latest",
+ "40GB"
+ ],
+ [
+ "70b",
+ "40GB"
+ ],
+ [
+ "70b-fp16",
+ "141GB"
+ ],
+ [
+ "70b-q2_K",
+ "26GB"
+ ],
+ [
+ "70b-q3_K_L",
+ "37GB"
+ ],
+ [
+ "70b-q3_K_M",
+ "34GB"
+ ],
+ [
+ "70b-q3_K_S",
+ "31GB"
+ ],
+ [
+ "70b-q4_0",
+ "40GB"
+ ],
+ [
+ "70b-q4_1",
+ "44GB"
+ ],
+ [
+ "70b-q4_K_M",
+ "43GB"
+ ],
+ [
+ "70b-q4_K_S",
+ "40GB"
+ ],
+ [
+ "70b-q5_0",
+ "49GB"
+ ],
+ [
+ "70b-q5_1",
+ "53GB"
+ ],
+ [
+ "70b-q5_K_M",
+ "50GB"
+ ],
+ [
+ "70b-q5_K_S",
+ "49GB"
+ ],
+ [
+ "70b-q6_K",
+ "58GB"
+ ],
+ [
+ "70b-q8_0",
+ "75GB"
+ ]
+ ],
+ "image": false,
+ "author": "Fireworks AI"
+ },
+ "nuextract": {
+ "url": "https://ollama.com/library/nuextract",
+ "description": "A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.",
+ "tags": [
+ [
+ "latest",
+ "2.2GB"
+ ],
+ [
+ "3.8b",
+ "2.2GB"
+ ],
+ [
+ "3.8b-fp16",
+ "7.6GB"
+ ],
+ [
+ "3.8b-q2_K",
+ "1.4GB"
+ ],
+ [
+ "3.8b-q3_K_L",
+ "2.1GB"
+ ],
+ [
+ "3.8b-q3_K_M",
+ "2.0GB"
+ ],
+ [
+ "3.8b-q3_K_S",
+ "1.7GB"
+ ],
+ [
+ "3.8b-q4_0",
+ "2.2GB"
+ ],
+ [
+ "3.8b-q4_1",
+ "2.4GB"
+ ],
+ [
+ "3.8b-q4_K_M",
+ "2.4GB"
+ ],
+ [
+ "3.8b-q4_K_S",
+ "2.2GB"
+ ],
+ [
+ "3.8b-q5_0",
+ "2.6GB"
+ ],
+ [
+ "3.8b-q5_1",
+ "2.9GB"
+ ],
+ [
+ "3.8b-q5_K_M",
+ "2.8GB"
+ ],
+ [
+ "3.8b-q5_K_S",
+ "2.6GB"
+ ],
+ [
+ "3.8b-q6_K",
+ "3.1GB"
+ ],
+ [
+ "3.8b-q8_0",
+ "4.1GB"
+ ]
+ ],
+ "image": false,
+ "author": "NuMind"
}
}
\ No newline at end of file
diff --git a/src/available_models_descriptions.py b/src/available_models_descriptions.py
index 4652a63..4069b31 100644
--- a/src/available_models_descriptions.py
+++ b/src/available_models_descriptions.py
@@ -16,80 +16,88 @@ descriptions = {
'llama2': _("Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters."),
'codellama': _("A large language model that can use text prompts to generate and discuss code."),
'dolphin-mixtral': _("Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford."),
+ 'nomic-embed-text': _("A high-performing open embedding model with a large token context window."),
'llama2-uncensored': _("Uncensored Llama 2 model by George Sung and Jarrad Hope."),
'deepseek-coder': _("DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens."),
- 'nomic-embed-text': _("A high-performing open embedding model with a large token context window."),
'phi': _("Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities."),
'dolphin-mistral': _("The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8."),
- 'mistral-openorca': _("Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset."),
'orca-mini': _("A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware."),
- 'mxbai-embed-large': _("State-of-the-art large embedding model from mixedbread.ai"),
'dolphin-llama3': _("Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills."),
+ 'mxbai-embed-large': _("State-of-the-art large embedding model from mixedbread.ai"),
+ 'mistral-openorca': _("Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset."),
'starcoder2': _("StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters."),
- 'llama2-chinese': _("Llama 2 based model fine tuned to improve Chinese dialogue ability."),
'zephyr': _("Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants."),
'yi': _("Yi 1.5 is a high-performing, bilingual language model."),
- 'nous-hermes2': _("The powerful family of models by Nous Research that excels at scientific discussion and coding tasks."),
+ 'llama2-chinese': _("Llama 2 based model fine tuned to improve Chinese dialogue ability."),
+ 'llava-llama3': _("A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks."),
'vicuna': _("General use chat model based on Llama and Llama 2 with 2K to 16K context sizes."),
+ 'nous-hermes2': _("The powerful family of models by Nous Research that excels at scientific discussion and coding tasks."),
'wizard-vicuna-uncensored': _("Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford."),
'tinyllama': _("The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens."),
- 'wizardlm2': _("State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases."),
- 'starcoder': _("StarCoder is a code generation model trained on 80+ programming languages."),
'codestral': _("Codestral is Mistral AI’s first-ever code model designed for code generation tasks."),
+ 'starcoder': _("StarCoder is a code generation model trained on 80+ programming languages."),
+ 'wizardlm2': _("State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases."),
'openchat': _("A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106."),
'tinydolphin': _("An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama."),
'openhermes': _("OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets."),
'wizardcoder': _("State-of-the-art code generation model"),
'stable-code': _("Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger."),
+ 'codeqwen': _("CodeQwen1.5 is a large language model pretrained on a large amount of code data."),
'neural-chat': _("A fine-tuned model based on Mistral with good coverage of domain and language."),
'wizard-math': _("Model focused on math and logic problems"),
- 'codeqwen': _("CodeQwen1.5 is a large language model pretrained on a large amount of code data."),
- 'phind-codellama': _("Code generation model based on Code Llama."),
'stablelm2': _("Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch."),
- 'dolphincoder': _("A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2."),
'all-minilm': _("Embedding models on very large sentence level datasets."),
+ 'granite-code': _("A family of open foundation models by IBM for Code Intelligence"),
+ 'phind-codellama': _("Code generation model based on Code Llama."),
+ 'dolphincoder': _("A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2."),
'nous-hermes': _("General use models based on Llama and Llama 2 from Nous Research."),
- 'starling-lm': _("Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness."),
'sqlcoder': _("SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks"),
- 'orca2': _("Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning."),
'llama3-gradient': _("This model extends LLama-3 8B's context length from 8k to over 1m tokens."),
+ 'starling-lm': _("Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness."),
'deepseek-llm': _("An advanced language model crafted with 2 trillion bilingual tokens."),
'yarn-llama2': _("An extension of Llama 2 that supports a context of up to 128k tokens."),
- 'llama3-chatqa': _("A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG)."),
- 'solar': _("A compact, yet powerful 10.7B large language model designed for single-turn conversation."),
'xwinlm': _("Conversational model based on Llama 2 that performs competitively on various benchmarks."),
- 'granite-code': _("A family of open foundation models by IBM for Code Intelligence"),
- 'dolphin-phi': _("2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research."),
+ 'llama3-chatqa': _("A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG)."),
+ 'orca2': _("Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning."),
+ 'solar': _("A compact, yet powerful 10.7B large language model designed for single-turn conversation."),
'wizardlm': _("General use model based on Llama 2."),
'samantha-mistral': _("A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral."),
+ 'dolphin-phi': _("2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research."),
'stable-beluga': _("Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy."),
- 'bakllava': _("BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture."),
- 'llava-llama3': _("A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks."),
- 'wizardlm-uncensored': _("Uncensored version of Wizard LM model"),
- 'medllama2': _("Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset."),
- 'nous-hermes2-mixtral': _("The Nous Hermes 2 model from Nous Research, now trained over Mixtral."),
- 'yarn-mistral': _("An extension of Mistral to support context windows of 64K or 128K."),
- 'snowflake-arctic-embed': _("A suite of text embedding models by Snowflake, optimized for performance."),
- 'llama-pro': _("An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics."),
- 'codeup': _("Great code generation model based on Llama2."),
- 'meditron': _("Open-source medical large language model adapted from Llama 2 to the medical domain."),
'moondream': _("moondream2 is a small vision language model designed to run efficiently on edge devices."),
- 'everythinglm': _("Uncensored Llama2 based model with support for a 16K context window."),
- 'nexusraven': _("Nexus Raven is a 13B instruction tuned model for function calling tasks."),
- 'magicoder': _("🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets."),
+ 'bakllava': _("BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture."),
+ 'wizardlm-uncensored': _("Uncensored version of Wizard LM model"),
+ 'snowflake-arctic-embed': _("A suite of text embedding models by Snowflake, optimized for performance."),
+ 'medllama2': _("Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset."),
+ 'yarn-mistral': _("An extension of Mistral to support context windows of 64K or 128K."),
+ 'nous-hermes2-mixtral': _("The Nous Hermes 2 model from Nous Research, now trained over Mixtral."),
+ 'llama-pro': _("An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics."),
'deepseek-v2': _("A strong, economical, and efficient Mixture-of-Experts language model."),
+ 'meditron': _("Open-source medical large language model adapted from Llama 2 to the medical domain."),
+ 'codeup': _("Great code generation model based on Llama2."),
+ 'nexusraven': _("Nexus Raven is a 13B instruction tuned model for function calling tasks."),
+ 'everythinglm': _("Uncensored Llama2 based model with support for a 16K context window."),
+ 'llava-phi3': _("A new small LLaVA model fine-tuned from Phi 3 Mini."),
+ 'magicoder': _("🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets."),
'stablelm-zephyr': _("A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware."),
'codebooga': _("A high-performing code instruct model created by merging two existing code models."),
- 'llava-phi3': _("A new small LLaVA model fine-tuned from Phi 3 Mini."),
'mistrallite': _("MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts."),
- 'wizard-vicuna': _("Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj."),
+ 'glm4': _("A strong multi-lingual general language model with competitive performance to Llama 3."),
+ 'wizard-vicuna': _("A strong multi-lingual general language model with competitive performance to Llama 3."),
'duckdb-nsql': _("7B parameter text-to-SQL model made by MotherDuck and Numbers Station."),
- 'goliath': _("A language model created by combining two fine-tuned Llama 2 70B models into one."),
'megadolphin': _("MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself."),
- 'open-orca-platypus2': _("Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation."),
+ 'goliath': _("A language model created by combining two fine-tuned Llama 2 70B models into one."),
'notux': _("A top-performing mixture of experts model, fine-tuned with high-quality data."),
+ 'open-orca-platypus2': _("Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation."),
+ 'falcon2': _("Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens."),
'notus': _("A 7B chat model fine-tuned with high-quality data and based on Zephyr."),
'dbrx': _("DBRX is an open, general-purpose LLM created by Databricks."),
- 'falcon2': _("Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens."),
+ 'codegeex4': _("A versatile model for AI software development scenarios, including code completion."),
'alfred': _("A robust conversational model designed to be used for both chat and instruct use cases."),
+ 'internlm2': _("InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability."),
+ 'llama3-groq-tool-use': _("A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling."),
+ 'mathstral': _("MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI."),
+ 'mistral-nemo': _("A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA."),
+ 'firefunction-v2': _("An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities."),
+ 'nuextract': _("A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3."),
}
\ No newline at end of file