diff --git a/src/available_models.json b/src/available_models.json index 3a2a621..00fd949 100644 --- a/src/available_models.json +++ b/src/available_models.json @@ -1,4 +1,264 @@ { + "llama3.2": { + "url": "https://ollama.com/library/llama3.2", + "description": "Meta's Llama 3.2 goes small with 1B and 3B models.", + "tags": [ + [ + "latest", + "2.0\u202fGB" + ], + [ + "1b", + "1.3\u202fGB" + ], + [ + "3b", + "2.0\u202fGB" + ], + [ + "1b-instruct-fp16", + "2.5\u202fGB" + ], + [ + "1b-instruct-q2_K", + "581\u202fMB" + ], + [ + "1b-instruct-q3_K_S", + "642\u202fMB" + ], + [ + "1b-instruct-q3_K_M", + "691\u202fMB" + ], + [ + "1b-instruct-q3_K_L", + "733\u202fMB" + ], + [ + "1b-instruct-q4_0", + "771\u202fMB" + ], + [ + "1b-instruct-q4_1", + "832\u202fMB" + ], + [ + "1b-instruct-q4_K_S", + "776\u202fMB" + ], + [ + "1b-instruct-q4_K_M", + "808\u202fMB" + ], + [ + "1b-instruct-q5_0", + "893\u202fMB" + ], + [ + "1b-instruct-q5_1", + "953\u202fMB" + ], + [ + "1b-instruct-q5_K_S", + "893\u202fMB" + ], + [ + "1b-instruct-q5_K_M", + "912\u202fMB" + ], + [ + "1b-instruct-q6_K", + "1.0\u202fGB" + ], + [ + "1b-instruct-q8_0", + "1.3\u202fGB" + ], + [ + "1b-text-fp16", + "2.5\u202fGB" + ], + [ + "1b-text-q2_K", + "581\u202fMB" + ], + [ + "1b-text-q3_K_S", + "642\u202fMB" + ], + [ + "1b-text-q3_K_M", + "691\u202fMB" + ], + [ + "1b-text-q3_K_L", + "733\u202fMB" + ], + [ + "1b-text-q4_0", + "771\u202fMB" + ], + [ + "1b-text-q4_1", + "832\u202fMB" + ], + [ + "1b-text-q4_K_S", + "776\u202fMB" + ], + [ + "1b-text-q4_K_M", + "808\u202fMB" + ], + [ + "1b-text-q5_0", + "893\u202fMB" + ], + [ + "1b-text-q5_1", + "953\u202fMB" + ], + [ + "1b-text-q5_K_S", + "893\u202fMB" + ], + [ + "1b-text-q5_K_M", + "912\u202fMB" + ], + [ + "1b-text-q6_K", + "1.0\u202fGB" + ], + [ + "1b-text-q8_0", + "1.3\u202fGB" + ], + [ + "3b-instruct-fp16", + "6.4\u202fGB" + ], + [ + "3b-instruct-q2_K", + "1.4\u202fGB" + ], + [ + "3b-instruct-q3_K_S", + "1.5\u202fGB" + ], + [ + "3b-instruct-q3_K_M", + "1.7\u202fGB" + ], + [ + "3b-instruct-q3_K_L", + "1.8\u202fGB" + ], + [ + "3b-instruct-q4_0", + "1.9\u202fGB" + ], + [ + "3b-instruct-q4_1", + "2.1\u202fGB" + ], + [ + "3b-instruct-q4_K_S", + "1.9\u202fGB" + ], + [ + "3b-instruct-q4_K_M", + "2.0\u202fGB" + ], + [ + "3b-instruct-q5_0", + "2.3\u202fGB" + ], + [ + "3b-instruct-q5_1", + "2.4\u202fGB" + ], + [ + "3b-instruct-q5_K_S", + "2.3\u202fGB" + ], + [ + "3b-instruct-q5_K_M", + "2.3\u202fGB" + ], + [ + "3b-instruct-q6_K", + "2.6\u202fGB" + ], + [ + "3b-instruct-q8_0", + "3.4\u202fGB" + ], + [ + "3b-text-fp16", + "6.4\u202fGB" + ], + [ + "3b-text-q2_K", + "1.4\u202fGB" + ], + [ + "3b-text-q3_K_S", + "1.5\u202fGB" + ], + [ + "3b-text-q3_K_M", + "1.7\u202fGB" + ], + [ + "3b-text-q3_K_L", + "1.8\u202fGB" + ], + [ + "3b-text-q4_0", + "1.9\u202fGB" + ], + [ + "3b-text-q4_1", + "2.1\u202fGB" + ], + [ + "3b-text-q4_K_S", + "1.9\u202fGB" + ], + [ + "3b-text-q4_K_M", + "2.0\u202fGB" + ], + [ + "3b-text-q5_0", + "2.3\u202fGB" + ], + [ + "3b-text-q5_1", + "2.4\u202fGB" + ], + [ + "3b-text-q5_K_S", + "2.3\u202fGB" + ], + [ + "3b-text-q5_K_M", + "2.3\u202fGB" + ], + [ + "3b-text-q6_K", + "2.6\u202fGB" + ], + [ + "3b-text-q8_0", + "3.4\u202fGB" + ] + ], + "image": false, + "author": "Meta" + }, "llama3.1": { "url": "https://ollama.com/library/llama3.1", "description": "Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.", @@ -144,11 +404,11 @@ "141\u202fGB" ], [ - "70b-instruct-q2_K", + "70b-instruct-q2_k", "26\u202fGB" ], [ - "70b-instruct-q2_k", + "70b-instruct-q2_K", "26\u202fGB" ], [ @@ -7635,6 +7895,30 @@ "image": false, "author": "Nomic AI" }, + "mxbai-embed-large": { + "url": "https://ollama.com/library/mxbai-embed-large", + "description": "State-of-the-art large embedding model from mixedbread.ai", + "tags": [ + [ + "latest", + "670\u202fMB" + ], + [ + "335m", + "670\u202fMB" + ], + [ + "v1", + "670\u202fMB" + ], + [ + "335m-v1-fp16", + "670\u202fMB" + ] + ], + "image": false, + "author": "Mixedbread.ai" + }, "dolphin-mixtral": { "url": "https://ollama.com/library/dolphin-mixtral", "description": "Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.", @@ -8071,150 +8355,6 @@ "image": false, "author": "Microsoft" }, - "llama2-uncensored": { - "url": "https://ollama.com/library/llama2-uncensored", - "description": "Uncensored Llama 2 model by George Sung and Jarrad Hope.", - "tags": [ - [ - "latest", - "3.8\u202fGB" - ], - [ - "7b", - "3.8\u202fGB" - ], - [ - "70b", - "39\u202fGB" - ], - [ - "7b-chat", - "3.8\u202fGB" - ], - [ - "70b-chat", - "39\u202fGB" - ], - [ - "7b-chat-fp16", - "13\u202fGB" - ], - [ - "7b-chat-q2_K", - "2.8\u202fGB" - ], - [ - "7b-chat-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-chat-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-chat-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-chat-q4_0", - "3.8\u202fGB" - ], - [ - "7b-chat-q4_1", - "4.2\u202fGB" - ], - [ - "7b-chat-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-chat-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-chat-q5_0", - "4.7\u202fGB" - ], - [ - "7b-chat-q5_1", - "5.1\u202fGB" - ], - [ - "7b-chat-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-chat-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-chat-q6_K", - "5.5\u202fGB" - ], - [ - "7b-chat-q8_0", - "7.2\u202fGB" - ], - [ - "70b-chat-q2_K", - "29\u202fGB" - ], - [ - "70b-chat-q3_K_S", - "30\u202fGB" - ], - [ - "70b-chat-q3_K_M", - "33\u202fGB" - ], - [ - "70b-chat-q3_K_L", - "36\u202fGB" - ], - [ - "70b-chat-q4_0", - "39\u202fGB" - ], - [ - "70b-chat-q4_1", - "43\u202fGB" - ], - [ - "70b-chat-q4_K_S", - "39\u202fGB" - ], - [ - "70b-chat-q4_K_M", - "41\u202fGB" - ], - [ - "70b-chat-q5_0", - "47\u202fGB" - ], - [ - "70b-chat-q5_1", - "52\u202fGB" - ], - [ - "70b-chat-q5_K_S", - "47\u202fGB" - ], - [ - "70b-chat-q5_K_M", - "49\u202fGB" - ], - [ - "70b-chat-q6_K", - "57\u202fGB" - ], - [ - "70b-chat-q8_0", - "73\u202fGB" - ] - ], - "image": false, - "author": "George Sung, Jarrad Hope" - }, "deepseek-coder": { "url": "https://ollama.com/library/deepseek-coder", "description": "DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.", @@ -8631,30 +8771,6 @@ "image": false, "author": "DeepSeek 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", - "670\u202fMB" - ], - [ - "335m", - "670\u202fMB" - ], - [ - "v1", - "670\u202fMB" - ], - [ - "335m-v1-fp16", - "670\u202fMB" - ] - ], - "image": false, - "author": "Mixedbread.ai" - }, "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.", @@ -8931,6 +9047,150 @@ "image": false, "author": "BigCode" }, + "llama2-uncensored": { + "url": "https://ollama.com/library/llama2-uncensored", + "description": "Uncensored Llama 2 model by George Sung and Jarrad Hope.", + "tags": [ + [ + "latest", + "3.8\u202fGB" + ], + [ + "7b", + "3.8\u202fGB" + ], + [ + "70b", + "39\u202fGB" + ], + [ + "7b-chat", + "3.8\u202fGB" + ], + [ + "70b-chat", + "39\u202fGB" + ], + [ + "7b-chat-fp16", + "13\u202fGB" + ], + [ + "7b-chat-q2_K", + "2.8\u202fGB" + ], + [ + "7b-chat-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-chat-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-chat-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-chat-q4_0", + "3.8\u202fGB" + ], + [ + "7b-chat-q4_1", + "4.2\u202fGB" + ], + [ + "7b-chat-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-chat-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-chat-q5_0", + "4.7\u202fGB" + ], + [ + "7b-chat-q5_1", + "5.1\u202fGB" + ], + [ + "7b-chat-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-chat-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-chat-q6_K", + "5.5\u202fGB" + ], + [ + "7b-chat-q8_0", + "7.2\u202fGB" + ], + [ + "70b-chat-q2_K", + "29\u202fGB" + ], + [ + "70b-chat-q3_K_S", + "30\u202fGB" + ], + [ + "70b-chat-q3_K_M", + "33\u202fGB" + ], + [ + "70b-chat-q3_K_L", + "36\u202fGB" + ], + [ + "70b-chat-q4_0", + "39\u202fGB" + ], + [ + "70b-chat-q4_1", + "43\u202fGB" + ], + [ + "70b-chat-q4_K_S", + "39\u202fGB" + ], + [ + "70b-chat-q4_K_M", + "41\u202fGB" + ], + [ + "70b-chat-q5_0", + "47\u202fGB" + ], + [ + "70b-chat-q5_1", + "52\u202fGB" + ], + [ + "70b-chat-q5_K_S", + "47\u202fGB" + ], + [ + "70b-chat-q5_K_M", + "49\u202fGB" + ], + [ + "70b-chat-q6_K", + "57\u202fGB" + ], + [ + "70b-chat-q8_0", + "73\u202fGB" + ] + ], + "image": false, + "author": "George Sung, Jarrad Hope" + }, "dolphin-mistral": { "url": "https://ollama.com/library/dolphin-mistral", "description": "The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.", @@ -9587,710 +9847,6 @@ "image": false, "author": "Hugging Face H4" }, - "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.", - "tags": [ - [ - "latest", - "4.7\u202fGB" - ], - [ - "8b", - "4.7\u202fGB" - ], - [ - "70b", - "40\u202fGB" - ], - [ - "v2.9", - "4.7\u202fGB" - ], - [ - "8b-256k", - "4.7\u202fGB" - ], - [ - "8b-256k-v2.9", - "4.7\u202fGB" - ], - [ - "8b-v2.9", - "4.7\u202fGB" - ], - [ - "70b-v2.9", - "40\u202fGB" - ], - [ - "8b-256k-v2.9-fp16", - "16\u202fGB" - ], - [ - "8b-256k-v2.9-q2_K", - "3.2\u202fGB" - ], - [ - "8b-256k-v2.9-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-256k-v2.9-q3_K_M", - "4.0\u202fGB" - ], - [ - "8b-256k-v2.9-q3_K_L", - "4.3\u202fGB" - ], - [ - "8b-256k-v2.9-q4_0", - "4.7\u202fGB" - ], - [ - "8b-256k-v2.9-q4_1", - "5.1\u202fGB" - ], - [ - "8b-256k-v2.9-q4_K_S", - "4.7\u202fGB" - ], - [ - "8b-256k-v2.9-q4_K_M", - "4.9\u202fGB" - ], - [ - "8b-256k-v2.9-q5_0", - "5.6\u202fGB" - ], - [ - "8b-256k-v2.9-q5_1", - "6.1\u202fGB" - ], - [ - "8b-256k-v2.9-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-256k-v2.9-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-256k-v2.9-q6_K", - "6.6\u202fGB" - ], - [ - "8b-256k-v2.9-q8_0", - "8.5\u202fGB" - ], - [ - "8b-v2.9-fp16", - "16\u202fGB" - ], - [ - "8b-v2.9-q2_K", - "3.2\u202fGB" - ], - [ - "8b-v2.9-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-v2.9-q3_K_M", - "4.0\u202fGB" - ], - [ - "8b-v2.9-q3_K_L", - "4.3\u202fGB" - ], - [ - "8b-v2.9-q4_0", - "4.7\u202fGB" - ], - [ - "8b-v2.9-q4_1", - "5.1\u202fGB" - ], - [ - "8b-v2.9-q4_K_S", - "4.7\u202fGB" - ], - [ - "8b-v2.9-q4_K_M", - "4.9\u202fGB" - ], - [ - "8b-v2.9-q5_0", - "5.6\u202fGB" - ], - [ - "8b-v2.9-q5_1", - "6.1\u202fGB" - ], - [ - "8b-v2.9-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-v2.9-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-v2.9-q6_K", - "6.6\u202fGB" - ], - [ - "8b-v2.9-q8_0", - "8.5\u202fGB" - ], - [ - "70b-v2.9-fp16", - "141\u202fGB" - ], - [ - "70b-v2.9-q2_K", - "26\u202fGB" - ], - [ - "70b-v2.9-q3_K_S", - "31\u202fGB" - ], - [ - "70b-v2.9-q3_K_M", - "34\u202fGB" - ], - [ - "70b-v2.9-q3_K_L", - "37\u202fGB" - ], - [ - "70b-v2.9-q4_0", - "40\u202fGB" - ], - [ - "70b-v2.9-q4_1", - "44\u202fGB" - ], - [ - "70b-v2.9-q4_K_S", - "40\u202fGB" - ], - [ - "70b-v2.9-q4_K_M", - "43\u202fGB" - ], - [ - "70b-v2.9-q5_0", - "49\u202fGB" - ], - [ - "70b-v2.9-q5_1", - "53\u202fGB" - ], - [ - "70b-v2.9-q5_K_S", - "49\u202fGB" - ], - [ - "70b-v2.9-q5_K_M", - "50\u202fGB" - ], - [ - "70b-v2.9-q6_K", - "58\u202fGB" - ], - [ - "70b-v2.9-q8_0", - "75\u202fGB" - ] - ], - "image": false, - "author": "Eric Hartford" - }, - "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.", - "tags": [ - [ - "latest", - "2.0\u202fGB" - ], - [ - "3b", - "2.0\u202fGB" - ], - [ - "7b", - "3.8\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "70b", - "39\u202fGB" - ], - [ - "7b-v3", - "3.8\u202fGB" - ], - [ - "13b-v3", - "7.4\u202fGB" - ], - [ - "70b-v3", - "39\u202fGB" - ], - [ - "3b-fp16", - "6.9\u202fGB" - ], - [ - "3b-q4_0", - "2.0\u202fGB" - ], - [ - "3b-q4_1", - "2.2\u202fGB" - ], - [ - "3b-q5_0", - "2.4\u202fGB" - ], - [ - "3b-q5_1", - "2.6\u202fGB" - ], - [ - "3b-q8_0", - "3.6\u202fGB" - ], - [ - "7b-fp16", - "13\u202fGB" - ], - [ - "7b-q2_K", - "2.8\u202fGB" - ], - [ - "7b-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-q4_0", - "3.8\u202fGB" - ], - [ - "7b-q4_1", - "4.2\u202fGB" - ], - [ - "7b-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-q5_0", - "4.7\u202fGB" - ], - [ - "7b-q5_1", - "5.1\u202fGB" - ], - [ - "7b-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-q6_K", - "5.5\u202fGB" - ], - [ - "7b-q8_0", - "7.2\u202fGB" - ], - [ - "13b-fp16", - "26\u202fGB" - ], - [ - "13b-q2_K", - "5.4\u202fGB" - ], - [ - "13b-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-q4_0", - "7.4\u202fGB" - ], - [ - "13b-q4_1", - "8.2\u202fGB" - ], - [ - "13b-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-q5_0", - "9.0\u202fGB" - ], - [ - "13b-q5_1", - "9.8\u202fGB" - ], - [ - "13b-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-q6_K", - "11\u202fGB" - ], - [ - "13b-q8_0", - "14\u202fGB" - ], - [ - "7b-v2-fp16", - "13\u202fGB" - ], - [ - "7b-v2-q2_K", - "2.8\u202fGB" - ], - [ - "7b-v2-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-v2-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-v2-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-v2-q4_0", - "3.8\u202fGB" - ], - [ - "7b-v2-q4_1", - "4.2\u202fGB" - ], - [ - "7b-v2-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-v2-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-v2-q5_0", - "4.7\u202fGB" - ], - [ - "7b-v2-q5_1", - "5.1\u202fGB" - ], - [ - "7b-v2-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-v2-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-v2-q6_K", - "5.5\u202fGB" - ], - [ - "7b-v2-q8_0", - "7.2\u202fGB" - ], - [ - "7b-v3-fp16", - "13\u202fGB" - ], - [ - "7b-v3-q2_K", - "2.8\u202fGB" - ], - [ - "7b-v3-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-v3-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-v3-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-v3-q4_0", - "3.8\u202fGB" - ], - [ - "7b-v3-q4_1", - "4.2\u202fGB" - ], - [ - "7b-v3-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-v3-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-v3-q5_0", - "4.7\u202fGB" - ], - [ - "7b-v3-q5_1", - "5.1\u202fGB" - ], - [ - "7b-v3-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-v3-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-v3-q6_K", - "5.5\u202fGB" - ], - [ - "7b-v3-q8_0", - "7.2\u202fGB" - ], - [ - "13b-v2-fp16", - "26\u202fGB" - ], - [ - "13b-v2-q2_K", - "5.4\u202fGB" - ], - [ - "13b-v2-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-v2-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-v2-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-v2-q4_0", - "7.4\u202fGB" - ], - [ - "13b-v2-q4_1", - "8.2\u202fGB" - ], - [ - "13b-v2-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-v2-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-v2-q5_0", - "9.0\u202fGB" - ], - [ - "13b-v2-q5_1", - "9.8\u202fGB" - ], - [ - "13b-v2-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-v2-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-v2-q6_K", - "11\u202fGB" - ], - [ - "13b-v2-q8_0", - "14\u202fGB" - ], - [ - "13b-v3-fp16", - "26\u202fGB" - ], - [ - "13b-v3-q2_K", - "5.4\u202fGB" - ], - [ - "13b-v3-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-v3-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-v3-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-v3-q4_0", - "7.4\u202fGB" - ], - [ - "13b-v3-q4_1", - "8.2\u202fGB" - ], - [ - "13b-v3-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-v3-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-v3-q5_0", - "9.0\u202fGB" - ], - [ - "13b-v3-q5_1", - "9.8\u202fGB" - ], - [ - "13b-v3-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-v3-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-v3-q6_K", - "11\u202fGB" - ], - [ - "13b-v3-q8_0", - "14\u202fGB" - ], - [ - "70b-v3-fp16", - "138\u202fGB" - ], - [ - "70b-v3-q2_K", - "29\u202fGB" - ], - [ - "70b-v3-q3_K_S", - "30\u202fGB" - ], - [ - "70b-v3-q3_K_M", - "33\u202fGB" - ], - [ - "70b-v3-q3_K_L", - "36\u202fGB" - ], - [ - "70b-v3-q4_0", - "39\u202fGB" - ], - [ - "70b-v3-q4_1", - "43\u202fGB" - ], - [ - "70b-v3-q4_K_S", - "39\u202fGB" - ], - [ - "70b-v3-q4_K_M", - "41\u202fGB" - ], - [ - "70b-v3-q5_0", - "47\u202fGB" - ], - [ - "70b-v3-q5_1", - "52\u202fGB" - ], - [ - "70b-v3-q5_K_S", - "47\u202fGB" - ], - [ - "70b-v3-q5_K_M", - "49\u202fGB" - ], - [ - "70b-v3-q6_K", - "57\u202fGB" - ], - [ - "70b-v3-q8_0", - "73\u202fGB" - ] - ], - "image": false, - "author": "Orca Mini Team" - }, "yi": { "url": "https://ollama.com/library/yi", "description": "Yi 1.5 is a high-performing, bilingual language model.", @@ -10995,6 +10551,710 @@ "image": false, "author": "01.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.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "8b", + "4.7\u202fGB" + ], + [ + "70b", + "40\u202fGB" + ], + [ + "v2.9", + "4.7\u202fGB" + ], + [ + "8b-256k", + "4.7\u202fGB" + ], + [ + "8b-256k-v2.9", + "4.7\u202fGB" + ], + [ + "8b-v2.9", + "4.7\u202fGB" + ], + [ + "70b-v2.9", + "40\u202fGB" + ], + [ + "8b-256k-v2.9-fp16", + "16\u202fGB" + ], + [ + "8b-256k-v2.9-q2_K", + "3.2\u202fGB" + ], + [ + "8b-256k-v2.9-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-256k-v2.9-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-256k-v2.9-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-256k-v2.9-q4_0", + "4.7\u202fGB" + ], + [ + "8b-256k-v2.9-q4_1", + "5.1\u202fGB" + ], + [ + "8b-256k-v2.9-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-256k-v2.9-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-256k-v2.9-q5_0", + "5.6\u202fGB" + ], + [ + "8b-256k-v2.9-q5_1", + "6.1\u202fGB" + ], + [ + "8b-256k-v2.9-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-256k-v2.9-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-256k-v2.9-q6_K", + "6.6\u202fGB" + ], + [ + "8b-256k-v2.9-q8_0", + "8.5\u202fGB" + ], + [ + "8b-v2.9-fp16", + "16\u202fGB" + ], + [ + "8b-v2.9-q2_K", + "3.2\u202fGB" + ], + [ + "8b-v2.9-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-v2.9-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-v2.9-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-v2.9-q4_0", + "4.7\u202fGB" + ], + [ + "8b-v2.9-q4_1", + "5.1\u202fGB" + ], + [ + "8b-v2.9-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-v2.9-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-v2.9-q5_0", + "5.6\u202fGB" + ], + [ + "8b-v2.9-q5_1", + "6.1\u202fGB" + ], + [ + "8b-v2.9-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-v2.9-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-v2.9-q6_K", + "6.6\u202fGB" + ], + [ + "8b-v2.9-q8_0", + "8.5\u202fGB" + ], + [ + "70b-v2.9-fp16", + "141\u202fGB" + ], + [ + "70b-v2.9-q2_K", + "26\u202fGB" + ], + [ + "70b-v2.9-q3_K_S", + "31\u202fGB" + ], + [ + "70b-v2.9-q3_K_M", + "34\u202fGB" + ], + [ + "70b-v2.9-q3_K_L", + "37\u202fGB" + ], + [ + "70b-v2.9-q4_0", + "40\u202fGB" + ], + [ + "70b-v2.9-q4_1", + "44\u202fGB" + ], + [ + "70b-v2.9-q4_K_S", + "40\u202fGB" + ], + [ + "70b-v2.9-q4_K_M", + "43\u202fGB" + ], + [ + "70b-v2.9-q5_0", + "49\u202fGB" + ], + [ + "70b-v2.9-q5_1", + "53\u202fGB" + ], + [ + "70b-v2.9-q5_K_S", + "49\u202fGB" + ], + [ + "70b-v2.9-q5_K_M", + "50\u202fGB" + ], + [ + "70b-v2.9-q6_K", + "58\u202fGB" + ], + [ + "70b-v2.9-q8_0", + "75\u202fGB" + ] + ], + "image": false, + "author": "Eric Hartford" + }, + "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.", + "tags": [ + [ + "latest", + "2.0\u202fGB" + ], + [ + "3b", + "2.0\u202fGB" + ], + [ + "7b", + "3.8\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "70b", + "39\u202fGB" + ], + [ + "7b-v3", + "3.8\u202fGB" + ], + [ + "13b-v3", + "7.4\u202fGB" + ], + [ + "70b-v3", + "39\u202fGB" + ], + [ + "3b-fp16", + "6.9\u202fGB" + ], + [ + "3b-q4_0", + "2.0\u202fGB" + ], + [ + "3b-q4_1", + "2.2\u202fGB" + ], + [ + "3b-q5_0", + "2.4\u202fGB" + ], + [ + "3b-q5_1", + "2.6\u202fGB" + ], + [ + "3b-q8_0", + "3.6\u202fGB" + ], + [ + "7b-fp16", + "13\u202fGB" + ], + [ + "7b-q2_K", + "2.8\u202fGB" + ], + [ + "7b-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-q4_0", + "3.8\u202fGB" + ], + [ + "7b-q4_1", + "4.2\u202fGB" + ], + [ + "7b-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-q5_0", + "4.7\u202fGB" + ], + [ + "7b-q5_1", + "5.1\u202fGB" + ], + [ + "7b-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-q6_K", + "5.5\u202fGB" + ], + [ + "7b-q8_0", + "7.2\u202fGB" + ], + [ + "13b-fp16", + "26\u202fGB" + ], + [ + "13b-q2_K", + "5.4\u202fGB" + ], + [ + "13b-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-q4_0", + "7.4\u202fGB" + ], + [ + "13b-q4_1", + "8.2\u202fGB" + ], + [ + "13b-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-q5_0", + "9.0\u202fGB" + ], + [ + "13b-q5_1", + "9.8\u202fGB" + ], + [ + "13b-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-q6_K", + "11\u202fGB" + ], + [ + "13b-q8_0", + "14\u202fGB" + ], + [ + "7b-v2-fp16", + "13\u202fGB" + ], + [ + "7b-v2-q2_K", + "2.8\u202fGB" + ], + [ + "7b-v2-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-v2-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-v2-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-v2-q4_0", + "3.8\u202fGB" + ], + [ + "7b-v2-q4_1", + "4.2\u202fGB" + ], + [ + "7b-v2-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-v2-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-v2-q5_0", + "4.7\u202fGB" + ], + [ + "7b-v2-q5_1", + "5.1\u202fGB" + ], + [ + "7b-v2-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-v2-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-v2-q6_K", + "5.5\u202fGB" + ], + [ + "7b-v2-q8_0", + "7.2\u202fGB" + ], + [ + "7b-v3-fp16", + "13\u202fGB" + ], + [ + "7b-v3-q2_K", + "2.8\u202fGB" + ], + [ + "7b-v3-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-v3-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-v3-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-v3-q4_0", + "3.8\u202fGB" + ], + [ + "7b-v3-q4_1", + "4.2\u202fGB" + ], + [ + "7b-v3-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-v3-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-v3-q5_0", + "4.7\u202fGB" + ], + [ + "7b-v3-q5_1", + "5.1\u202fGB" + ], + [ + "7b-v3-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-v3-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-v3-q6_K", + "5.5\u202fGB" + ], + [ + "7b-v3-q8_0", + "7.2\u202fGB" + ], + [ + "13b-v2-fp16", + "26\u202fGB" + ], + [ + "13b-v2-q2_K", + "5.4\u202fGB" + ], + [ + "13b-v2-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-v2-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-v2-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-v2-q4_0", + "7.4\u202fGB" + ], + [ + "13b-v2-q4_1", + "8.2\u202fGB" + ], + [ + "13b-v2-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-v2-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-v2-q5_0", + "9.0\u202fGB" + ], + [ + "13b-v2-q5_1", + "9.8\u202fGB" + ], + [ + "13b-v2-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-v2-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-v2-q6_K", + "11\u202fGB" + ], + [ + "13b-v2-q8_0", + "14\u202fGB" + ], + [ + "13b-v3-fp16", + "26\u202fGB" + ], + [ + "13b-v3-q2_K", + "5.4\u202fGB" + ], + [ + "13b-v3-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-v3-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-v3-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-v3-q4_0", + "7.4\u202fGB" + ], + [ + "13b-v3-q4_1", + "8.2\u202fGB" + ], + [ + "13b-v3-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-v3-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-v3-q5_0", + "9.0\u202fGB" + ], + [ + "13b-v3-q5_1", + "9.8\u202fGB" + ], + [ + "13b-v3-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-v3-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-v3-q6_K", + "11\u202fGB" + ], + [ + "13b-v3-q8_0", + "14\u202fGB" + ], + [ + "70b-v3-fp16", + "138\u202fGB" + ], + [ + "70b-v3-q2_K", + "29\u202fGB" + ], + [ + "70b-v3-q3_K_S", + "30\u202fGB" + ], + [ + "70b-v3-q3_K_M", + "33\u202fGB" + ], + [ + "70b-v3-q3_K_L", + "36\u202fGB" + ], + [ + "70b-v3-q4_0", + "39\u202fGB" + ], + [ + "70b-v3-q4_1", + "43\u202fGB" + ], + [ + "70b-v3-q4_K_S", + "39\u202fGB" + ], + [ + "70b-v3-q4_K_M", + "41\u202fGB" + ], + [ + "70b-v3-q5_0", + "47\u202fGB" + ], + [ + "70b-v3-q5_1", + "52\u202fGB" + ], + [ + "70b-v3-q5_K_S", + "47\u202fGB" + ], + [ + "70b-v3-q5_K_M", + "49\u202fGB" + ], + [ + "70b-v3-q6_K", + "57\u202fGB" + ], + [ + "70b-v3-q8_0", + "73\u202fGB" + ] + ], + "image": false, + "author": "Orca Mini Team" + }, "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.", @@ -11019,6 +11279,282 @@ "image": true, "author": "Xtuner" }, + "qwen2.5-coder": { + "url": "https://ollama.com/library/qwen2.5-coder", + "description": "The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.", + "tags": [ + [ + "latest", + "4.7\u202fGB" + ], + [ + "1.5b", + "986\u202fMB" + ], + [ + "7b", + "4.7\u202fGB" + ], + [ + "1.5b-base", + "986\u202fMB" + ], + [ + "1.5b-instruct", + "986\u202fMB" + ], + [ + "7b-base", + "4.7\u202fGB" + ], + [ + "7b-instruct", + "4.7\u202fGB" + ], + [ + "1.5b-base-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-base-q2_K", + "676\u202fMB" + ], + [ + "1.5b-base-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-base-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-base-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-base-q4_0", + "935\u202fMB" + ], + [ + "1.5b-base-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-base-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-base-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-base-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-base-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-base-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-base-q8_0", + "1.6\u202fGB" + ], + [ + "1.5b-instruct-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-instruct-q2_K", + "676\u202fMB" + ], + [ + "1.5b-instruct-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-instruct-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-instruct-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-instruct-q4_0", + "935\u202fMB" + ], + [ + "1.5b-instruct-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-instruct-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-instruct-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-instruct-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-instruct-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-instruct-q8_0", + "1.6\u202fGB" + ], + [ + "7b-base-fp16", + "15\u202fGB" + ], + [ + "7b-base-q2_K", + "3.0\u202fGB" + ], + [ + "7b-base-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-base-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-base-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-base-q4_0", + "4.4\u202fGB" + ], + [ + "7b-base-q4_1", + "4.9\u202fGB" + ], + [ + "7b-base-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-base-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-base-q5_0", + "5.3\u202fGB" + ], + [ + "7b-base-q5_1", + "5.8\u202fGB" + ], + [ + "7b-base-q5_K_S", + "5.3\u202fGB" + ], + [ + "7b-base-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-base-q6_K", + "6.3\u202fGB" + ], + [ + "7b-base-q8_0", + "8.1\u202fGB" + ], + [ + "7b-instruct-fp16", + "15\u202fGB" + ], + [ + "7b-instruct-q2_K", + "3.0\u202fGB" + ], + [ + "7b-instruct-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-instruct-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-instruct-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-instruct-q4_0", + "4.4\u202fGB" + ], + [ + "7b-instruct-q4_1", + "4.9\u202fGB" + ], + [ + "7b-instruct-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-instruct-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-instruct-q5_0", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_1", + "5.8\u202fGB" + ], + [ + "7b-instruct-q5_K_S", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-instruct-q6_K", + "6.3\u202fGB" + ], + [ + "7b-instruct-q8_0", + "8.1\u202fGB" + ] + ], + "image": false, + "author": "Alibaba" + }, "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.", @@ -11655,6 +12191,82 @@ "image": false, "author": "TinyLlama Team" }, + "codestral": { + "url": "https://ollama.com/library/codestral", + "description": "Codestral is Mistral AI\u2019s first-ever code model designed for code generation tasks.", + "tags": [ + [ + "latest", + "13\u202fGB" + ], + [ + "22b", + "13\u202fGB" + ], + [ + "v0.1", + "13\u202fGB" + ], + [ + "22b-v0.1-q2_K", + "8.3\u202fGB" + ], + [ + "22b-v0.1-q3_K_S", + "9.6\u202fGB" + ], + [ + "22b-v0.1-q3_K_M", + "11\u202fGB" + ], + [ + "22b-v0.1-q3_K_L", + "12\u202fGB" + ], + [ + "22b-v0.1-q4_0", + "13\u202fGB" + ], + [ + "22b-v0.1-q4_1", + "14\u202fGB" + ], + [ + "22b-v0.1-q4_K_S", + "13\u202fGB" + ], + [ + "22b-v0.1-q4_K_M", + "13\u202fGB" + ], + [ + "22b-v0.1-q5_0", + "15\u202fGB" + ], + [ + "22b-v0.1-q5_1", + "17\u202fGB" + ], + [ + "22b-v0.1-q5_K_S", + "15\u202fGB" + ], + [ + "22b-v0.1-q5_K_M", + "16\u202fGB" + ], + [ + "22b-v0.1-q6_K", + "18\u202fGB" + ], + [ + "22b-v0.1-q8_0", + "24\u202fGB" + ] + ], + "image": false, + "author": "Mistral AI" + }, "vicuna": { "url": "https://ollama.com/library/vicuna", "description": "General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.", @@ -12107,82 +12719,6 @@ "image": false, "author": "lmsys.org" }, - "codestral": { - "url": "https://ollama.com/library/codestral", - "description": "Codestral is Mistral AI\u2019s first-ever code model designed for code generation tasks.", - "tags": [ - [ - "latest", - "13\u202fGB" - ], - [ - "22b", - "13\u202fGB" - ], - [ - "v0.1", - "13\u202fGB" - ], - [ - "22b-v0.1-q2_K", - "8.3\u202fGB" - ], - [ - "22b-v0.1-q3_K_S", - "9.6\u202fGB" - ], - [ - "22b-v0.1-q3_K_M", - "11\u202fGB" - ], - [ - "22b-v0.1-q3_K_L", - "12\u202fGB" - ], - [ - "22b-v0.1-q4_0", - "13\u202fGB" - ], - [ - "22b-v0.1-q4_1", - "14\u202fGB" - ], - [ - "22b-v0.1-q4_K_S", - "13\u202fGB" - ], - [ - "22b-v0.1-q4_K_M", - "13\u202fGB" - ], - [ - "22b-v0.1-q5_0", - "15\u202fGB" - ], - [ - "22b-v0.1-q5_1", - "17\u202fGB" - ], - [ - "22b-v0.1-q5_K_S", - "15\u202fGB" - ], - [ - "22b-v0.1-q5_K_M", - "16\u202fGB" - ], - [ - "22b-v0.1-q6_K", - "18\u202fGB" - ], - [ - "22b-v0.1-q8_0", - "24\u202fGB" - ] - ], - "image": false, - "author": "Mistral AI" - }, "llama2-chinese": { "url": "https://ollama.com/library/llama2-chinese", "description": "Llama 2 based model fine tuned to improve Chinese dialogue ability.", @@ -12331,6 +12867,78 @@ "image": false, "author": "Meta" }, + "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", + "669\u202fMB" + ], + [ + "22m", + "46\u202fMB" + ], + [ + "33m", + "67\u202fMB" + ], + [ + "110m", + "219\u202fMB" + ], + [ + "137m", + "274\u202fMB" + ], + [ + "335m", + "669\u202fMB" + ], + [ + "l", + "669\u202fMB" + ], + [ + "m", + "219\u202fMB" + ], + [ + "m-long", + "274\u202fMB" + ], + [ + "s", + "67\u202fMB" + ], + [ + "xs", + "46\u202fMB" + ], + [ + "22m-xs-fp16", + "46\u202fMB" + ], + [ + "33m-s-fp16", + "67\u202fMB" + ], + [ + "110m-m-fp16", + "219\u202fMB" + ], + [ + "137m-m-long-fp16", + "274\u202fMB" + ], + [ + "335m-l-fp16", + "669\u202fMB" + ] + ], + "image": false, + "author": "Snowflake" + }, "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.", @@ -12535,222 +13143,6 @@ "image": false, "author": "Eric Hartford" }, - "codegeex4": { - "url": "https://ollama.com/library/codegeex4", - "description": "A versatile model for AI software development scenarios, including code completion.", - "tags": [ - [ - "latest", - "5.5\u202fGB" - ], - [ - "9b", - "5.5\u202fGB" - ], - [ - "9b-all-fp16", - "19\u202fGB" - ], - [ - "9b-all-q2_K", - "4.0\u202fGB" - ], - [ - "9b-all-q3_K_S", - "4.6\u202fGB" - ], - [ - "9b-all-q3_K_M", - "5.1\u202fGB" - ], - [ - "9b-all-q3_K_L", - "5.3\u202fGB" - ], - [ - "9b-all-q4_0", - "5.5\u202fGB" - ], - [ - "9b-all-q4_1", - "6.0\u202fGB" - ], - [ - "9b-all-q4_K_S", - "5.8\u202fGB" - ], - [ - "9b-all-q4_K_M", - "6.3\u202fGB" - ], - [ - "9b-all-q5_0", - "6.6\u202fGB" - ], - [ - "9b-all-q5_1", - "7.1\u202fGB" - ], - [ - "9b-all-q5_K_S", - "6.7\u202fGB" - ], - [ - "9b-all-q5_K_M", - "7.1\u202fGB" - ], - [ - "9b-all-q6_K", - "8.3\u202fGB" - ], - [ - "9b-all-q8_0", - "10.0\u202fGB" - ] - ], - "image": false, - "author": "THUDM" - }, - "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.", - "tags": [ - [ - "latest", - "6.1\u202fGB" - ], - [ - "10.7b", - "6.1\u202fGB" - ], - [ - "34b", - "19\u202fGB" - ], - [ - "10.7b-solar-fp16", - "21\u202fGB" - ], - [ - "10.7b-solar-q2_K", - "4.5\u202fGB" - ], - [ - "10.7b-solar-q3_K_S", - "4.7\u202fGB" - ], - [ - "10.7b-solar-q3_K_M", - "5.2\u202fGB" - ], - [ - "10.7b-solar-q3_K_L", - "5.7\u202fGB" - ], - [ - "10.7b-solar-q4_0", - "6.1\u202fGB" - ], - [ - "10.7b-solar-q4_1", - "6.7\u202fGB" - ], - [ - "10.7b-solar-q4_K_S", - "6.1\u202fGB" - ], - [ - "10.7b-solar-q4_K_M", - "6.5\u202fGB" - ], - [ - "10.7b-solar-q5_0", - "7.4\u202fGB" - ], - [ - "10.7b-solar-q5_1", - "8.1\u202fGB" - ], - [ - "10.7b-solar-q5_K_S", - "7.4\u202fGB" - ], - [ - "10.7b-solar-q5_K_M", - "7.6\u202fGB" - ], - [ - "10.7b-solar-q6_K", - "8.8\u202fGB" - ], - [ - "10.7b-solar-q8_0", - "11\u202fGB" - ], - [ - "34b-yi-fp16", - "69\u202fGB" - ], - [ - "34b-yi-q2_K", - "15\u202fGB" - ], - [ - "34b-yi-q3_K_S", - "15\u202fGB" - ], - [ - "34b-yi-q3_K_M", - "17\u202fGB" - ], - [ - "34b-yi-q3_K_L", - "18\u202fGB" - ], - [ - "34b-yi-q4_0", - "19\u202fGB" - ], - [ - "34b-yi-q4_1", - "22\u202fGB" - ], - [ - "34b-yi-q4_K_S", - "20\u202fGB" - ], - [ - "34b-yi-q4_K_M", - "21\u202fGB" - ], - [ - "34b-yi-q5_0", - "24\u202fGB" - ], - [ - "34b-yi-q5_1", - "26\u202fGB" - ], - [ - "34b-yi-q5_K_S", - "24\u202fGB" - ], - [ - "34b-yi-q5_K_M", - "24\u202fGB" - ], - [ - "34b-yi-q6_K", - "28\u202fGB" - ], - [ - "34b-yi-q8_0", - "37\u202fGB" - ] - ], - "image": false, - "author": "Nous Research" - }, "granite-code": { "url": "https://ollama.com/library/granite-code", "description": "A family of open foundation models by IBM for Code Intelligence", @@ -13407,6 +13799,270 @@ "image": false, "author": "IBM for Code Intelligence" }, + "codegeex4": { + "url": "https://ollama.com/library/codegeex4", + "description": "A versatile model for AI software development scenarios, including code completion.", + "tags": [ + [ + "latest", + "5.5\u202fGB" + ], + [ + "9b", + "5.5\u202fGB" + ], + [ + "9b-all-fp16", + "19\u202fGB" + ], + [ + "9b-all-q2_K", + "4.0\u202fGB" + ], + [ + "9b-all-q3_K_S", + "4.6\u202fGB" + ], + [ + "9b-all-q3_K_M", + "5.1\u202fGB" + ], + [ + "9b-all-q3_K_L", + "5.3\u202fGB" + ], + [ + "9b-all-q4_0", + "5.5\u202fGB" + ], + [ + "9b-all-q4_1", + "6.0\u202fGB" + ], + [ + "9b-all-q4_K_S", + "5.8\u202fGB" + ], + [ + "9b-all-q4_K_M", + "6.3\u202fGB" + ], + [ + "9b-all-q5_0", + "6.6\u202fGB" + ], + [ + "9b-all-q5_1", + "7.1\u202fGB" + ], + [ + "9b-all-q5_K_S", + "6.7\u202fGB" + ], + [ + "9b-all-q5_K_M", + "7.1\u202fGB" + ], + [ + "9b-all-q6_K", + "8.3\u202fGB" + ], + [ + "9b-all-q8_0", + "10.0\u202fGB" + ] + ], + "image": false, + "author": "THUDM" + }, + "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.", + "tags": [ + [ + "latest", + "6.1\u202fGB" + ], + [ + "10.7b", + "6.1\u202fGB" + ], + [ + "34b", + "19\u202fGB" + ], + [ + "10.7b-solar-fp16", + "21\u202fGB" + ], + [ + "10.7b-solar-q2_K", + "4.5\u202fGB" + ], + [ + "10.7b-solar-q3_K_S", + "4.7\u202fGB" + ], + [ + "10.7b-solar-q3_K_M", + "5.2\u202fGB" + ], + [ + "10.7b-solar-q3_K_L", + "5.7\u202fGB" + ], + [ + "10.7b-solar-q4_0", + "6.1\u202fGB" + ], + [ + "10.7b-solar-q4_1", + "6.7\u202fGB" + ], + [ + "10.7b-solar-q4_K_S", + "6.1\u202fGB" + ], + [ + "10.7b-solar-q4_K_M", + "6.5\u202fGB" + ], + [ + "10.7b-solar-q5_0", + "7.4\u202fGB" + ], + [ + "10.7b-solar-q5_1", + "8.1\u202fGB" + ], + [ + "10.7b-solar-q5_K_S", + "7.4\u202fGB" + ], + [ + "10.7b-solar-q5_K_M", + "7.6\u202fGB" + ], + [ + "10.7b-solar-q6_K", + "8.8\u202fGB" + ], + [ + "10.7b-solar-q8_0", + "11\u202fGB" + ], + [ + "34b-yi-fp16", + "69\u202fGB" + ], + [ + "34b-yi-q2_K", + "15\u202fGB" + ], + [ + "34b-yi-q3_K_S", + "15\u202fGB" + ], + [ + "34b-yi-q3_K_M", + "17\u202fGB" + ], + [ + "34b-yi-q3_K_L", + "18\u202fGB" + ], + [ + "34b-yi-q4_0", + "19\u202fGB" + ], + [ + "34b-yi-q4_1", + "22\u202fGB" + ], + [ + "34b-yi-q4_K_S", + "20\u202fGB" + ], + [ + "34b-yi-q4_K_M", + "21\u202fGB" + ], + [ + "34b-yi-q5_0", + "24\u202fGB" + ], + [ + "34b-yi-q5_1", + "26\u202fGB" + ], + [ + "34b-yi-q5_K_S", + "24\u202fGB" + ], + [ + "34b-yi-q5_K_M", + "24\u202fGB" + ], + [ + "34b-yi-q6_K", + "28\u202fGB" + ], + [ + "34b-yi-q8_0", + "37\u202fGB" + ] + ], + "image": false, + "author": "Nous Research" + }, + "all-minilm": { + "url": "https://ollama.com/library/all-minilm", + "description": "Embedding models on very large sentence level datasets.", + "tags": [ + [ + "latest", + "46\u202fMB" + ], + [ + "22m", + "46\u202fMB" + ], + [ + "33m", + "67\u202fMB" + ], + [ + "l12", + "67\u202fMB" + ], + [ + "l12-v2", + "67\u202fMB" + ], + [ + "l6", + "46\u202fMB" + ], + [ + "l6-v2", + "46\u202fMB" + ], + [ + "v2", + "46\u202fMB" + ], + [ + "22m-l6-v2-fp16", + "46\u202fMB" + ], + [ + "33m-l12-v2-fp16", + "67\u202fMB" + ] + ], + "image": false, + "author": "Sentence Transformers" + }, "openchat": { "url": "https://ollama.com/library/openchat", "description": "A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.", @@ -13755,102 +14411,6 @@ "image": false, "author": "Cohere" }, - "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", - "4.1\u202fGB" - ], - [ - "7b", - "4.1\u202fGB" - ], - [ - "8x22b", - "80\u202fGB" - ], - [ - "7b-fp16", - "14\u202fGB" - ], - [ - "7b-q2_K", - "2.7\u202fGB" - ], - [ - "7b-q3_K_S", - "3.2\u202fGB" - ], - [ - "7b-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-q3_K_L", - "3.8\u202fGB" - ], - [ - "7b-q4_0", - "4.1\u202fGB" - ], - [ - "7b-q4_1", - "4.6\u202fGB" - ], - [ - "7b-q4_K_S", - "4.1\u202fGB" - ], - [ - "7b-q4_K_M", - "4.4\u202fGB" - ], - [ - "7b-q5_0", - "5.0\u202fGB" - ], - [ - "7b-q5_1", - "5.4\u202fGB" - ], - [ - "7b-q5_K_S", - "5.0\u202fGB" - ], - [ - "7b-q5_K_M", - "5.1\u202fGB" - ], - [ - "7b-q6_K", - "5.9\u202fGB" - ], - [ - "7b-q8_0", - "7.7\u202fGB" - ], - [ - "8x22b-fp16", - "281\u202fGB" - ], - [ - "8x22b-q2_K", - "52\u202fGB" - ], - [ - "8x22b-q4_0", - "80\u202fGB" - ], - [ - "8x22b-q8_0", - "149\u202fGB" - ] - ], - "image": false, - "author": "Microsoft" - }, "codeqwen": { "url": "https://ollama.com/library/codeqwen", "description": "CodeQwen1.5 is a large language model pretrained on a large amount of code data.", @@ -13979,6 +14539,102 @@ "image": false, "author": "Alibaba" }, + "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", + "4.1\u202fGB" + ], + [ + "7b", + "4.1\u202fGB" + ], + [ + "8x22b", + "80\u202fGB" + ], + [ + "7b-fp16", + "14\u202fGB" + ], + [ + "7b-q2_K", + "2.7\u202fGB" + ], + [ + "7b-q3_K_S", + "3.2\u202fGB" + ], + [ + "7b-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-q3_K_L", + "3.8\u202fGB" + ], + [ + "7b-q4_0", + "4.1\u202fGB" + ], + [ + "7b-q4_1", + "4.6\u202fGB" + ], + [ + "7b-q4_K_S", + "4.1\u202fGB" + ], + [ + "7b-q4_K_M", + "4.4\u202fGB" + ], + [ + "7b-q5_0", + "5.0\u202fGB" + ], + [ + "7b-q5_1", + "5.4\u202fGB" + ], + [ + "7b-q5_K_S", + "5.0\u202fGB" + ], + [ + "7b-q5_K_M", + "5.1\u202fGB" + ], + [ + "7b-q6_K", + "5.9\u202fGB" + ], + [ + "7b-q8_0", + "7.7\u202fGB" + ], + [ + "8x22b-fp16", + "281\u202fGB" + ], + [ + "8x22b-q2_K", + "52\u202fGB" + ], + [ + "8x22b-q4_0", + "80\u202fGB" + ], + [ + "8x22b-q8_0", + "149\u202fGB" + ] + ], + "image": false, + "author": "Microsoft" + }, "tinydolphin": { "url": "https://ollama.com/library/tinydolphin", "description": "An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.", @@ -14059,54 +14715,6 @@ "image": false, "author": "Eric Hartford" }, - "all-minilm": { - "url": "https://ollama.com/library/all-minilm", - "description": "Embedding models on very large sentence level datasets.", - "tags": [ - [ - "latest", - "46\u202fMB" - ], - [ - "22m", - "46\u202fMB" - ], - [ - "33m", - "67\u202fMB" - ], - [ - "l12", - "67\u202fMB" - ], - [ - "l12-v2", - "67\u202fMB" - ], - [ - "l6", - "46\u202fMB" - ], - [ - "l6-v2", - "46\u202fMB" - ], - [ - "v2", - "46\u202fMB" - ], - [ - "22m-l6-v2-fp16", - "46\u202fMB" - ], - [ - "33m-l12-v2-fp16", - "67\u202fMB" - ] - ], - "image": false, - "author": "Sentence Transformers" - }, "wizardcoder": { "url": "https://ollama.com/library/wizardcoder", "description": "State-of-the-art code generation model", @@ -14683,6 +15291,222 @@ "image": false, "author": "Teknium" }, + "qwen2-math": { + "url": "https://ollama.com/library/qwen2-math", + "description": "Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).", + "tags": [ + [ + "latest", + "4.4\u202fGB" + ], + [ + "1.5b", + "935\u202fMB" + ], + [ + "7b", + "4.4\u202fGB" + ], + [ + "72b", + "41\u202fGB" + ], + [ + "1.5b-instruct", + "935\u202fMB" + ], + [ + "7b-instruct", + "4.4\u202fGB" + ], + [ + "72b-instruct", + "41\u202fGB" + ], + [ + "1.5b-instruct-fp16", + "3.1\u202fGB" + ], + [ + "1.5b-instruct-q2_K", + "676\u202fMB" + ], + [ + "1.5b-instruct-q3_K_S", + "761\u202fMB" + ], + [ + "1.5b-instruct-q3_K_M", + "824\u202fMB" + ], + [ + "1.5b-instruct-q3_K_L", + "880\u202fMB" + ], + [ + "1.5b-instruct-q4_0", + "935\u202fMB" + ], + [ + "1.5b-instruct-q4_1", + "1.0\u202fGB" + ], + [ + "1.5b-instruct-q4_K_S", + "940\u202fMB" + ], + [ + "1.5b-instruct-q4_K_M", + "986\u202fMB" + ], + [ + "1.5b-instruct-q5_0", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_1", + "1.2\u202fGB" + ], + [ + "1.5b-instruct-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-instruct-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-instruct-q8_0", + "1.6\u202fGB" + ], + [ + "7b-instruct-fp16", + "15\u202fGB" + ], + [ + "7b-instruct-q2_K", + "3.0\u202fGB" + ], + [ + "7b-instruct-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-instruct-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-instruct-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-instruct-q4_0", + "4.4\u202fGB" + ], + [ + "7b-instruct-q4_1", + "4.9\u202fGB" + ], + [ + "7b-instruct-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-instruct-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-instruct-q5_0", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_1", + "5.8\u202fGB" + ], + [ + "7b-instruct-q5_K_S", + "5.3\u202fGB" + ], + [ + "7b-instruct-q5_K_M", + "5.4\u202fGB" + ], + [ + "7b-instruct-q6_K", + "6.3\u202fGB" + ], + [ + "7b-instruct-q8_0", + "8.1\u202fGB" + ], + [ + "72b-instruct-fp16", + "145\u202fGB" + ], + [ + "72b-instruct-q2_K", + "30\u202fGB" + ], + [ + "72b-instruct-q3_K_S", + "34\u202fGB" + ], + [ + "72b-instruct-q3_K_M", + "38\u202fGB" + ], + [ + "72b-instruct-q3_K_L", + "40\u202fGB" + ], + [ + "72b-instruct-q4_0", + "41\u202fGB" + ], + [ + "72b-instruct-q4_1", + "46\u202fGB" + ], + [ + "72b-instruct-q4_K_S", + "44\u202fGB" + ], + [ + "72b-instruct-q4_K_M", + "47\u202fGB" + ], + [ + "72b-instruct-q5_0", + "50\u202fGB" + ], + [ + "72b-instruct-q5_1", + "55\u202fGB" + ], + [ + "72b-instruct-q5_K_S", + "51\u202fGB" + ], + [ + "72b-instruct-q5_K_M", + "54\u202fGB" + ], + [ + "72b-instruct-q6_K", + "64\u202fGB" + ], + [ + "72b-instruct-q8_0", + "77\u202fGB" + ] + ], + "image": false, + "author": "Alibaba" + }, "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.", @@ -15103,221 +15927,417 @@ "image": false, "author": "Stability AI" }, - "qwen2-math": { - "url": "https://ollama.com/library/qwen2-math", - "description": "Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).", + "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.", "tags": [ [ "latest", - "4.4\u202fGB" - ], - [ - "1.5b", - "935\u202fMB" - ], - [ - "7b", - "4.4\u202fGB" - ], - [ - "72b", - "41\u202fGB" - ], - [ - "1.5b-instruct", - "935\u202fMB" - ], - [ - "7b-instruct", - "4.4\u202fGB" - ], - [ - "72b-instruct", - "41\u202fGB" - ], - [ - "1.5b-instruct-fp16", - "3.1\u202fGB" - ], - [ - "1.5b-instruct-q2_K", - "676\u202fMB" - ], - [ - "1.5b-instruct-q3_K_S", - "761\u202fMB" - ], - [ - "1.5b-instruct-q3_K_M", - "824\u202fMB" - ], - [ - "1.5b-instruct-q3_K_L", - "880\u202fMB" - ], - [ - "1.5b-instruct-q4_0", - "935\u202fMB" - ], - [ - "1.5b-instruct-q4_1", - "1.0\u202fGB" - ], - [ - "1.5b-instruct-q4_K_S", - "940\u202fMB" - ], - [ - "1.5b-instruct-q4_K_M", - "986\u202fMB" - ], - [ - "1.5b-instruct-q5_0", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q5_1", - "1.2\u202fGB" - ], - [ - "1.5b-instruct-q5_K_S", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q5_K_M", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q6_K", - "1.3\u202fGB" - ], - [ - "1.5b-instruct-q8_0", - "1.6\u202fGB" - ], - [ - "7b-instruct-fp16", - "15\u202fGB" - ], - [ - "7b-instruct-q2_K", - "3.0\u202fGB" - ], - [ - "7b-instruct-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-instruct-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-instruct-q3_K_L", - "4.1\u202fGB" - ], - [ - "7b-instruct-q4_0", - "4.4\u202fGB" - ], - [ - "7b-instruct-q4_1", - "4.9\u202fGB" - ], - [ - "7b-instruct-q4_K_S", - "4.5\u202fGB" - ], - [ - "7b-instruct-q4_K_M", "4.7\u202fGB" ], [ - "7b-instruct-q5_0", - "5.3\u202fGB" + "1048k", + "4.7\u202fGB" ], [ - "7b-instruct-q5_1", - "5.8\u202fGB" + "8b", + "4.7\u202fGB" ], [ - "7b-instruct-q5_K_S", - "5.3\u202fGB" - ], - [ - "7b-instruct-q5_K_M", - "5.4\u202fGB" - ], - [ - "7b-instruct-q6_K", - "6.3\u202fGB" - ], - [ - "7b-instruct-q8_0", - "8.1\u202fGB" - ], - [ - "72b-instruct-fp16", - "145\u202fGB" - ], - [ - "72b-instruct-q2_K", - "30\u202fGB" - ], - [ - "72b-instruct-q3_K_S", - "34\u202fGB" - ], - [ - "72b-instruct-q3_K_M", - "38\u202fGB" - ], - [ - "72b-instruct-q3_K_L", + "70b", "40\u202fGB" ], [ - "72b-instruct-q4_0", - "41\u202fGB" + "instruct", + "4.7\u202fGB" ], [ - "72b-instruct-q4_1", - "46\u202fGB" + "8b-instruct-1048k-fp16", + "16\u202fGB" ], [ - "72b-instruct-q4_K_S", + "8b-instruct-1048k-q2_K", + "3.2\u202fGB" + ], + [ + "8b-instruct-1048k-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-instruct-1048k-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-instruct-1048k-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-instruct-1048k-q4_0", + "4.7\u202fGB" + ], + [ + "8b-instruct-1048k-q4_1", + "5.1\u202fGB" + ], + [ + "8b-instruct-1048k-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-instruct-1048k-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-instruct-1048k-q5_0", + "5.6\u202fGB" + ], + [ + "8b-instruct-1048k-q5_1", + "6.1\u202fGB" + ], + [ + "8b-instruct-1048k-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-instruct-1048k-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-instruct-1048k-q6_K", + "6.6\u202fGB" + ], + [ + "8b-instruct-1048k-q8_0", + "8.5\u202fGB" + ], + [ + "70b-instruct-1048k-fp16", + "141\u202fGB" + ], + [ + "70b-instruct-1048k-q2_K", + "26\u202fGB" + ], + [ + "70b-instruct-1048k-q3_K_S", + "31\u202fGB" + ], + [ + "70b-instruct-1048k-q3_K_M", + "34\u202fGB" + ], + [ + "70b-instruct-1048k-q3_K_L", + "37\u202fGB" + ], + [ + "70b-instruct-1048k-q4_0", + "40\u202fGB" + ], + [ + "70b-instruct-1048k-q4_1", "44\u202fGB" ], [ - "72b-instruct-q4_K_M", - "47\u202fGB" + "70b-instruct-1048k-q4_K_S", + "40\u202fGB" ], [ - "72b-instruct-q5_0", + "70b-instruct-1048k-q4_K_M", + "43\u202fGB" + ], + [ + "70b-instruct-1048k-q5_0", + "49\u202fGB" + ], + [ + "70b-instruct-1048k-q5_1", + "53\u202fGB" + ], + [ + "70b-instruct-1048k-q5_K_S", + "49\u202fGB" + ], + [ + "70b-instruct-1048k-q5_K_M", "50\u202fGB" ], [ - "72b-instruct-q5_1", - "55\u202fGB" + "70b-instruct-1048k-q6_K", + "58\u202fGB" ], [ - "72b-instruct-q5_K_S", - "51\u202fGB" - ], - [ - "72b-instruct-q5_K_M", - "54\u202fGB" - ], - [ - "72b-instruct-q6_K", - "64\u202fGB" - ], - [ - "72b-instruct-q8_0", - "77\u202fGB" + "70b-instruct-1048k-q8_0", + "75\u202fGB" ] ], "image": false, - "author": "Alibaba" + "author": "Gradient AI" + }, + "deepseek-llm": { + "url": "https://ollama.com/library/deepseek-llm", + "description": "An advanced language model crafted with 2 trillion bilingual tokens.", + "tags": [ + [ + "latest", + "4.0\u202fGB" + ], + [ + "7b", + "4.0\u202fGB" + ], + [ + "67b", + "38\u202fGB" + ], + [ + "7b-base", + "4.0\u202fGB" + ], + [ + "7b-chat", + "4.0\u202fGB" + ], + [ + "67b-base", + "38\u202fGB" + ], + [ + "67b-chat", + "38\u202fGB" + ], + [ + "7b-base-fp16", + "14\u202fGB" + ], + [ + "7b-base-q2_K", + "3.0\u202fGB" + ], + [ + "7b-base-q3_K_S", + "3.1\u202fGB" + ], + [ + "7b-base-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-base-q3_K_L", + "3.7\u202fGB" + ], + [ + "7b-base-q4_0", + "4.0\u202fGB" + ], + [ + "7b-base-q4_1", + "4.4\u202fGB" + ], + [ + "7b-base-q4_K_S", + "4.0\u202fGB" + ], + [ + "7b-base-q4_K_M", + "4.2\u202fGB" + ], + [ + "7b-base-q5_0", + "4.8\u202fGB" + ], + [ + "7b-base-q5_1", + "5.2\u202fGB" + ], + [ + "7b-base-q5_K_S", + "4.8\u202fGB" + ], + [ + "7b-base-q5_K_M", + "4.9\u202fGB" + ], + [ + "7b-base-q6_K", + "5.7\u202fGB" + ], + [ + "7b-base-q8_0", + "7.3\u202fGB" + ], + [ + "7b-chat-fp16", + "14\u202fGB" + ], + [ + "7b-chat-q2_K", + "3.0\u202fGB" + ], + [ + "7b-chat-q3_K_S", + "3.1\u202fGB" + ], + [ + "7b-chat-q3_K_M", + "3.5\u202fGB" + ], + [ + "7b-chat-q3_K_L", + "3.7\u202fGB" + ], + [ + "7b-chat-q4_0", + "4.0\u202fGB" + ], + [ + "7b-chat-q4_1", + "4.4\u202fGB" + ], + [ + "7b-chat-q4_K_S", + "4.0\u202fGB" + ], + [ + "7b-chat-q4_K_M", + "4.2\u202fGB" + ], + [ + "7b-chat-q5_0", + "4.8\u202fGB" + ], + [ + "7b-chat-q5_1", + "5.2\u202fGB" + ], + [ + "7b-chat-q5_K_S", + "4.8\u202fGB" + ], + [ + "7b-chat-q5_K_M", + "4.9\u202fGB" + ], + [ + "7b-chat-q6_K", + "5.7\u202fGB" + ], + [ + "7b-chat-q8_0", + "7.3\u202fGB" + ], + [ + "67b-base-fp16", + "135\u202fGB" + ], + [ + "67b-base-q2_K", + "28\u202fGB" + ], + [ + "67b-base-q3_K_S", + "29\u202fGB" + ], + [ + "67b-base-q3_K_M", + "33\u202fGB" + ], + [ + "67b-base-q3_K_L", + "36\u202fGB" + ], + [ + "67b-base-q4_0", + "38\u202fGB" + ], + [ + "67b-base-q4_1", + "42\u202fGB" + ], + [ + "67b-base-q4_K_S", + "38\u202fGB" + ], + [ + "67b-base-q4_K_M", + "40\u202fGB" + ], + [ + "67b-base-q5_0", + "46\u202fGB" + ], + [ + "67b-base-q5_1", + "51\u202fGB" + ], + [ + "67b-base-q5_K_S", + "46\u202fGB" + ], + [ + "67b-base-q5_K_M", + "48\u202fGB" + ], + [ + "67b-base-q6_K", + "55\u202fGB" + ], + [ + "67b-base-q8_0", + "72\u202fGB" + ], + [ + "67b-chat-fp16", + "135\u202fGB" + ], + [ + "67b-chat-q2_K", + "28\u202fGB" + ], + [ + "67b-chat-q3_K_S", + "29\u202fGB" + ], + [ + "67b-chat-q3_K_M", + "33\u202fGB" + ], + [ + "67b-chat-q3_K_L", + "36\u202fGB" + ], + [ + "67b-chat-q4_0", + "38\u202fGB" + ], + [ + "67b-chat-q4_1", + "42\u202fGB" + ], + [ + "67b-chat-q4_K_S", + "38\u202fGB" + ], + [ + "67b-chat-q4_K_M", + "40\u202fGB" + ], + [ + "67b-chat-q5_0", + "46\u202fGB" + ], + [ + "67b-chat-q5_1", + "51\u202fGB" + ], + [ + "67b-chat-q5_K_S", + "46\u202fGB" + ] + ], + "image": false, + "author": "DeepSeek Team" }, "wizard-math": { "url": "https://ollama.com/library/wizard-math", @@ -15583,153 +16603,141 @@ "image": false, "author": "WizardLM Team" }, - "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.", + "glm4": { + "url": "https://ollama.com/library/glm4", + "description": "A strong multi-lingual general language model with competitive performance to Llama 3.", "tags": [ [ "latest", - "4.7\u202fGB" + "5.5\u202fGB" ], [ - "1048k", - "4.7\u202fGB" + "9b", + "5.5\u202fGB" ], [ - "8b", - "4.7\u202fGB" + "9b-chat-fp16", + "19\u202fGB" ], [ - "70b", - "40\u202fGB" - ], - [ - "instruct", - "4.7\u202fGB" - ], - [ - "8b-instruct-1048k-fp16", - "16\u202fGB" - ], - [ - "8b-instruct-1048k-q2_K", - "3.2\u202fGB" - ], - [ - "8b-instruct-1048k-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-instruct-1048k-q3_K_M", + "9b-chat-q2_K", "4.0\u202fGB" ], [ - "8b-instruct-1048k-q3_K_L", - "4.3\u202fGB" + "9b-chat-q3_K_S", + "4.6\u202fGB" ], [ - "8b-instruct-1048k-q4_0", - "4.7\u202fGB" - ], - [ - "8b-instruct-1048k-q4_1", + "9b-chat-q3_K_M", "5.1\u202fGB" ], [ - "8b-instruct-1048k-q4_K_S", - "4.7\u202fGB" + "9b-chat-q3_K_L", + "5.3\u202fGB" ], [ - "8b-instruct-1048k-q4_K_M", - "4.9\u202fGB" + "9b-chat-q4_0", + "5.5\u202fGB" ], [ - "8b-instruct-1048k-q5_0", - "5.6\u202fGB" + "9b-chat-q4_1", + "6.0\u202fGB" ], [ - "8b-instruct-1048k-q5_1", - "6.1\u202fGB" + "9b-chat-q4_K_S", + "5.8\u202fGB" ], [ - "8b-instruct-1048k-q5_K_S", - "5.6\u202fGB" + "9b-chat-q4_K_M", + "6.3\u202fGB" ], [ - "8b-instruct-1048k-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-instruct-1048k-q6_K", + "9b-chat-q5_0", "6.6\u202fGB" ], [ - "8b-instruct-1048k-q8_0", - "8.5\u202fGB" + "9b-chat-q5_1", + "7.1\u202fGB" ], [ - "70b-instruct-1048k-fp16", - "141\u202fGB" + "9b-chat-q5_K_S", + "6.7\u202fGB" ], [ - "70b-instruct-1048k-q2_K", - "26\u202fGB" + "9b-chat-q5_K_M", + "7.1\u202fGB" ], [ - "70b-instruct-1048k-q3_K_S", - "31\u202fGB" + "9b-chat-q6_K", + "8.3\u202fGB" ], [ - "70b-instruct-1048k-q3_K_M", - "34\u202fGB" + "9b-chat-q8_0", + "10.0\u202fGB" ], [ - "70b-instruct-1048k-q3_K_L", - "37\u202fGB" + "9b-text-fp16", + "19\u202fGB" ], [ - "70b-instruct-1048k-q4_0", - "40\u202fGB" + "9b-text-q2_K", + "4.0\u202fGB" ], [ - "70b-instruct-1048k-q4_1", - "44\u202fGB" + "9b-text-q3_K_S", + "4.6\u202fGB" ], [ - "70b-instruct-1048k-q4_K_S", - "40\u202fGB" + "9b-text-q3_K_M", + "5.1\u202fGB" ], [ - "70b-instruct-1048k-q4_K_M", - "43\u202fGB" + "9b-text-q3_K_L", + "5.3\u202fGB" ], [ - "70b-instruct-1048k-q5_0", - "49\u202fGB" + "9b-text-q4_0", + "5.5\u202fGB" ], [ - "70b-instruct-1048k-q5_1", - "53\u202fGB" + "9b-text-q4_1", + "6.0\u202fGB" ], [ - "70b-instruct-1048k-q5_K_S", - "49\u202fGB" + "9b-text-q4_K_S", + "5.8\u202fGB" ], [ - "70b-instruct-1048k-q5_K_M", - "50\u202fGB" + "9b-text-q4_K_M", + "6.3\u202fGB" ], [ - "70b-instruct-1048k-q6_K", - "58\u202fGB" + "9b-text-q5_0", + "6.6\u202fGB" ], [ - "70b-instruct-1048k-q8_0", - "75\u202fGB" + "9b-text-q5_1", + "7.1\u202fGB" + ], + [ + "9b-text-q5_K_S", + "6.7\u202fGB" + ], + [ + "9b-text-q5_K_M", + "7.1\u202fGB" + ], + [ + "9b-text-q6_K", + "8.3\u202fGB" + ], + [ + "9b-text-q8_0", + "10.0\u202fGB" ] ], "image": false, - "author": "Gradient AI" + "author": "THUDM" }, "neural-chat": { "url": "https://ollama.com/library/neural-chat", @@ -15939,269 +16947,713 @@ "image": false, "author": "Intel" }, - "deepseek-llm": { - "url": "https://ollama.com/library/deepseek-llm", - "description": "An advanced language model crafted with 2 trillion bilingual tokens.", + "reflection": { + "url": "https://ollama.com/library/reflection", + "description": "A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.", "tags": [ [ "latest", - "4.0\u202fGB" - ], - [ - "7b", - "4.0\u202fGB" - ], - [ - "67b", - "38\u202fGB" - ], - [ - "7b-base", - "4.0\u202fGB" - ], - [ - "7b-chat", - "4.0\u202fGB" - ], - [ - "67b-base", - "38\u202fGB" - ], - [ - "67b-chat", - "38\u202fGB" - ], - [ - "7b-base-fp16", - "14\u202fGB" - ], - [ - "7b-base-q2_K", - "3.0\u202fGB" - ], - [ - "7b-base-q3_K_S", - "3.1\u202fGB" - ], - [ - "7b-base-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-base-q3_K_L", - "3.7\u202fGB" - ], - [ - "7b-base-q4_0", - "4.0\u202fGB" - ], - [ - "7b-base-q4_1", - "4.4\u202fGB" - ], - [ - "7b-base-q4_K_S", - "4.0\u202fGB" - ], - [ - "7b-base-q4_K_M", - "4.2\u202fGB" - ], - [ - "7b-base-q5_0", - "4.8\u202fGB" - ], - [ - "7b-base-q5_1", - "5.2\u202fGB" - ], - [ - "7b-base-q5_K_S", - "4.8\u202fGB" - ], - [ - "7b-base-q5_K_M", - "4.9\u202fGB" - ], - [ - "7b-base-q6_K", - "5.7\u202fGB" - ], - [ - "7b-base-q8_0", - "7.3\u202fGB" - ], - [ - "7b-chat-fp16", - "14\u202fGB" - ], - [ - "7b-chat-q2_K", - "3.0\u202fGB" - ], - [ - "7b-chat-q3_K_S", - "3.1\u202fGB" - ], - [ - "7b-chat-q3_K_M", - "3.5\u202fGB" - ], - [ - "7b-chat-q3_K_L", - "3.7\u202fGB" - ], - [ - "7b-chat-q4_0", - "4.0\u202fGB" - ], - [ - "7b-chat-q4_1", - "4.4\u202fGB" - ], - [ - "7b-chat-q4_K_S", - "4.0\u202fGB" - ], - [ - "7b-chat-q4_K_M", - "4.2\u202fGB" - ], - [ - "7b-chat-q5_0", - "4.8\u202fGB" - ], - [ - "7b-chat-q5_1", - "5.2\u202fGB" - ], - [ - "7b-chat-q5_K_S", - "4.8\u202fGB" - ], - [ - "7b-chat-q5_K_M", - "4.9\u202fGB" - ], - [ - "7b-chat-q6_K", - "5.7\u202fGB" - ], - [ - "7b-chat-q8_0", - "7.3\u202fGB" - ], - [ - "67b-base-fp16", - "135\u202fGB" - ], - [ - "67b-base-q2_K", - "28\u202fGB" - ], - [ - "67b-base-q3_K_S", - "29\u202fGB" - ], - [ - "67b-base-q3_K_M", - "33\u202fGB" - ], - [ - "67b-base-q3_K_L", - "36\u202fGB" - ], - [ - "67b-base-q4_0", - "38\u202fGB" - ], - [ - "67b-base-q4_1", - "42\u202fGB" - ], - [ - "67b-base-q4_K_S", - "38\u202fGB" - ], - [ - "67b-base-q4_K_M", "40\u202fGB" ], [ - "67b-base-q5_0", - "46\u202fGB" - ], - [ - "67b-base-q5_1", - "51\u202fGB" - ], - [ - "67b-base-q5_K_S", - "46\u202fGB" - ], - [ - "67b-base-q5_K_M", - "48\u202fGB" - ], - [ - "67b-base-q6_K", - "55\u202fGB" - ], - [ - "67b-base-q8_0", - "72\u202fGB" - ], - [ - "67b-chat-fp16", - "135\u202fGB" - ], - [ - "67b-chat-q2_K", - "28\u202fGB" - ], - [ - "67b-chat-q3_K_S", - "29\u202fGB" - ], - [ - "67b-chat-q3_K_M", - "33\u202fGB" - ], - [ - "67b-chat-q3_K_L", - "36\u202fGB" - ], - [ - "67b-chat-q4_0", - "38\u202fGB" - ], - [ - "67b-chat-q4_1", - "42\u202fGB" - ], - [ - "67b-chat-q4_K_S", - "38\u202fGB" - ], - [ - "67b-chat-q4_K_M", + "70b", "40\u202fGB" ], [ - "67b-chat-q5_0", - "46\u202fGB" + "70b-fp16", + "141\u202fGB" ], [ - "67b-chat-q5_1", - "51\u202fGB" + "70b-q2_K", + "26\u202fGB" ], [ - "67b-chat-q5_K_S", - "46\u202fGB" + "70b-q3_K_S", + "31\u202fGB" + ], + [ + "70b-q3_K_M", + "34\u202fGB" + ], + [ + "70b-q3_K_L", + "37\u202fGB" + ], + [ + "70b-q4_0", + "40\u202fGB" + ], + [ + "70b-q4_1", + "44\u202fGB" + ], + [ + "70b-q4_K_S", + "40\u202fGB" + ], + [ + "70b-q4_K_M", + "43\u202fGB" + ], + [ + "70b-q5_0", + "49\u202fGB" + ], + [ + "70b-q5_1", + "53\u202fGB" + ], + [ + "70b-q5_K_S", + "49\u202fGB" + ], + [ + "70b-q5_K_M", + "50\u202fGB" + ], + [ + "70b-q6_K", + "58\u202fGB" + ], + [ + "70b-q8_0", + "75\u202fGB" ] ], "image": false, - "author": "DeepSeek Team" + "author": "Mattshumer" + }, + "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", + "4.7\u202fGB" + ], + [ + "8b", + "4.7\u202fGB" + ], + [ + "70b", + "40\u202fGB" + ], + [ + "8b-v1.5", + "4.7\u202fGB" + ], + [ + "70b-v1.5", + "40\u202fGB" + ], + [ + "8b-v1.5-fp16", + "16\u202fGB" + ], + [ + "8b-v1.5-q2_K", + "3.2\u202fGB" + ], + [ + "8b-v1.5-q3_K_S", + "3.7\u202fGB" + ], + [ + "8b-v1.5-q3_K_M", + "4.0\u202fGB" + ], + [ + "8b-v1.5-q3_K_L", + "4.3\u202fGB" + ], + [ + "8b-v1.5-q4_0", + "4.7\u202fGB" + ], + [ + "8b-v1.5-q4_1", + "5.1\u202fGB" + ], + [ + "8b-v1.5-q4_K_S", + "4.7\u202fGB" + ], + [ + "8b-v1.5-q4_K_M", + "4.9\u202fGB" + ], + [ + "8b-v1.5-q5_0", + "5.6\u202fGB" + ], + [ + "8b-v1.5-q5_1", + "6.1\u202fGB" + ], + [ + "8b-v1.5-q5_K_S", + "5.6\u202fGB" + ], + [ + "8b-v1.5-q5_K_M", + "5.7\u202fGB" + ], + [ + "8b-v1.5-q6_K", + "6.6\u202fGB" + ], + [ + "8b-v1.5-q8_0", + "8.5\u202fGB" + ], + [ + "70b-v1.5-fp16", + "141\u202fGB" + ], + [ + "70b-v1.5-q2_K", + "26\u202fGB" + ], + [ + "70b-v1.5-q3_K_S", + "31\u202fGB" + ], + [ + "70b-v1.5-q3_K_M", + "34\u202fGB" + ], + [ + "70b-v1.5-q3_K_L", + "37\u202fGB" + ], + [ + "70b-v1.5-q4_0", + "40\u202fGB" + ], + [ + "70b-v1.5-q4_1", + "44\u202fGB" + ], + [ + "70b-v1.5-q4_K_S", + "40\u202fGB" + ], + [ + "70b-v1.5-q4_K_M", + "43\u202fGB" + ], + [ + "70b-v1.5-q5_0", + "49\u202fGB" + ], + [ + "70b-v1.5-q5_1", + "53\u202fGB" + ], + [ + "70b-v1.5-q5_K_S", + "49\u202fGB" + ], + [ + "70b-v1.5-q5_K_M", + "50\u202fGB" + ], + [ + "70b-v1.5-q6_K", + "58\u202fGB" + ], + [ + "70b-v1.5-q8_0", + "75\u202fGB" + ] + ], + "image": false, + "author": "Nvidia" + }, + "mistral-large": { + "url": "https://ollama.com/library/mistral-large", + "description": "Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.", + "tags": [ + [ + "latest", + "69\u202fGB" + ], + [ + "123b", + "69\u202fGB" + ], + [ + "123b-instruct-2407-fp16", + "245\u202fGB" + ], + [ + "123b-instruct-2407-q2_K", + "45\u202fGB" + ], + [ + "123b-instruct-2407-q3_K_S", + "53\u202fGB" + ], + [ + "123b-instruct-2407-q3_K_M", + "59\u202fGB" + ], + [ + "123b-instruct-2407-q3_K_L", + "65\u202fGB" + ], + [ + "123b-instruct-2407-q4_0", + "69\u202fGB" + ], + [ + "123b-instruct-2407-q4_1", + "77\u202fGB" + ], + [ + "123b-instruct-2407-q4_K_S", + "70\u202fGB" + ], + [ + "123b-instruct-2407-q4_K_M", + "73\u202fGB" + ], + [ + "123b-instruct-2407-q5_0", + "84\u202fGB" + ], + [ + "123b-instruct-2407-q5_1", + "92\u202fGB" + ], + [ + "123b-instruct-2407-q5_K_S", + "84\u202fGB" + ], + [ + "123b-instruct-2407-q5_K_M", + "86\u202fGB" + ], + [ + "123b-instruct-2407-q6_K", + "101\u202fGB" + ], + [ + "123b-instruct-2407-q8_0", + "130\u202fGB" + ] + ], + "image": false, + "author": "Mistral 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", + "1.7\u202fGB" + ], + [ + "1.8b", + "1.7\u202fGB" + ], + [ + "v2", + "1.7\u202fGB" + ], + [ + "1.8b-v2-fp16", + "3.7\u202fGB" + ], + [ + "1.8b-v2-q2_K", + "1.5\u202fGB" + ], + [ + "1.8b-v2-q3_K_S", + "1.6\u202fGB" + ], + [ + "1.8b-v2-q3_K_M", + "1.7\u202fGB" + ], + [ + "1.8b-v2-q3_K_L", + "1.7\u202fGB" + ], + [ + "1.8b-v2-q4_0", + "1.7\u202fGB" + ], + [ + "1.8b-v2-q4_1", + "1.8\u202fGB" + ], + [ + "1.8b-v2-q4_K_S", + "1.7\u202fGB" + ], + [ + "1.8b-v2-q4_K_M", + "1.8\u202fGB" + ], + [ + "1.8b-v2-q5_0", + "1.9\u202fGB" + ], + [ + "1.8b-v2-q5_1", + "2.0\u202fGB" + ], + [ + "1.8b-v2-q5_K_S", + "1.9\u202fGB" + ], + [ + "1.8b-v2-q5_K_M", + "2.0\u202fGB" + ], + [ + "1.8b-v2-q6_K", + "2.1\u202fGB" + ], + [ + "1.8b-v2-q8_0", + "2.4\u202fGB" + ] + ], + "image": true, + "author": "Vikhyatk" + }, + "xwinlm": { + "url": "https://ollama.com/library/xwinlm", + "description": "Conversational model based on Llama 2 that performs competitively on various benchmarks.", + "tags": [ + [ + "latest", + "3.8\u202fGB" + ], + [ + "7b", + "3.8\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "7b-v0.1", + "3.8\u202fGB" + ], + [ + "7b-v0.2", + "3.8\u202fGB" + ], + [ + "13b-v0.1", + "7.4\u202fGB" + ], + [ + "13b-v0.2", + "7.4\u202fGB" + ], + [ + "70b-v0.1", + "39\u202fGB" + ], + [ + "7b-v0.1-fp16", + "13\u202fGB" + ], + [ + "7b-v0.1-q2_K", + "2.8\u202fGB" + ], + [ + "7b-v0.1-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-v0.1-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-v0.1-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-v0.1-q4_0", + "3.8\u202fGB" + ], + [ + "7b-v0.1-q4_1", + "4.2\u202fGB" + ], + [ + "7b-v0.1-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-v0.1-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-v0.1-q5_0", + "4.7\u202fGB" + ], + [ + "7b-v0.1-q5_1", + "5.1\u202fGB" + ], + [ + "7b-v0.1-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-v0.1-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-v0.1-q6_K", + "5.5\u202fGB" + ], + [ + "7b-v0.1-q8_0", + "7.2\u202fGB" + ], + [ + "7b-v0.2-fp16", + "13\u202fGB" + ], + [ + "7b-v0.2-q2_K", + "2.8\u202fGB" + ], + [ + "7b-v0.2-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-v0.2-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-v0.2-q4_0", + "3.8\u202fGB" + ], + [ + "7b-v0.2-q4_1", + "4.2\u202fGB" + ], + [ + "7b-v0.2-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-v0.2-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-v0.2-q5_0", + "4.7\u202fGB" + ], + [ + "7b-v0.2-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-v0.2-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-v0.2-q6_K", + "5.5\u202fGB" + ], + [ + "7b-v0.2-q8_0", + "7.2\u202fGB" + ], + [ + "13b-v0.1-fp16", + "26\u202fGB" + ], + [ + "13b-v0.1-q2_K", + "5.4\u202fGB" + ], + [ + "13b-v0.1-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-v0.1-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-v0.1-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-v0.1-q4_0", + "7.4\u202fGB" + ], + [ + "13b-v0.1-q4_1", + "8.2\u202fGB" + ], + [ + "13b-v0.1-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-v0.1-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-v0.1-q5_0", + "9.0\u202fGB" + ], + [ + "13b-v0.1-q5_1", + "9.8\u202fGB" + ], + [ + "13b-v0.1-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-v0.1-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-v0.1-q6_K", + "11\u202fGB" + ], + [ + "13b-v0.1-q8_0", + "14\u202fGB" + ], + [ + "13b-v0.2-fp16", + "26\u202fGB" + ], + [ + "13b-v0.2-q2_K", + "5.4\u202fGB" + ], + [ + "13b-v0.2-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-v0.2-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-v0.2-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-v0.2-q4_0", + "7.4\u202fGB" + ], + [ + "13b-v0.2-q4_1", + "8.2\u202fGB" + ], + [ + "13b-v0.2-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-v0.2-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-v0.2-q5_0", + "9.0\u202fGB" + ], + [ + "13b-v0.2-q5_1", + "9.8\u202fGB" + ], + [ + "13b-v0.2-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-v0.2-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-v0.2-q6_K", + "11\u202fGB" + ], + [ + "13b-v0.2-q8_0", + "14\u202fGB" + ], + [ + "70b-v0.1-fp16", + "138\u202fGB" + ], + [ + "70b-v0.1-q2_K", + "29\u202fGB" + ], + [ + "70b-v0.1-q3_K_S", + "30\u202fGB" + ], + [ + "70b-v0.1-q3_K_M", + "33\u202fGB" + ], + [ + "70b-v0.1-q3_K_L", + "36\u202fGB" + ], + [ + "70b-v0.1-q4_0", + "39\u202fGB" + ], + [ + "70b-v0.1-q4_1", + "43\u202fGB" + ], + [ + "70b-v0.1-q4_K_S", + "39\u202fGB" + ], + [ + "70b-v0.1-q4_K_M", + "41\u202fGB" + ], + [ + "70b-v0.1-q5_0", + "47\u202fGB" + ], + [ + "70b-v0.1-q5_1", + "52\u202fGB" + ], + [ + "70b-v0.1-q5_K_S", + "47\u202fGB" + ], + [ + "70b-v0.1-q6_K", + "57\u202fGB" + ], + [ + "70b-v0.1-q8_0", + "73\u202fGB" + ] + ], + "image": false, + "author": "Xwin LM" }, "phind-codellama": { "url": "https://ollama.com/library/phind-codellama", @@ -16667,334 +18119,6 @@ "image": false, "author": "Nous Research" }, - "xwinlm": { - "url": "https://ollama.com/library/xwinlm", - "description": "Conversational model based on Llama 2 that performs competitively on various benchmarks.", - "tags": [ - [ - "latest", - "3.8\u202fGB" - ], - [ - "7b", - "3.8\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "7b-v0.1", - "3.8\u202fGB" - ], - [ - "7b-v0.2", - "3.8\u202fGB" - ], - [ - "13b-v0.1", - "7.4\u202fGB" - ], - [ - "13b-v0.2", - "7.4\u202fGB" - ], - [ - "70b-v0.1", - "39\u202fGB" - ], - [ - "7b-v0.1-fp16", - "13\u202fGB" - ], - [ - "7b-v0.1-q2_K", - "2.8\u202fGB" - ], - [ - "7b-v0.1-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-v0.1-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-v0.1-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-v0.1-q4_0", - "3.8\u202fGB" - ], - [ - "7b-v0.1-q4_1", - "4.2\u202fGB" - ], - [ - "7b-v0.1-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-v0.1-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-v0.1-q5_0", - "4.7\u202fGB" - ], - [ - "7b-v0.1-q5_1", - "5.1\u202fGB" - ], - [ - "7b-v0.1-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-v0.1-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-v0.1-q6_K", - "5.5\u202fGB" - ], - [ - "7b-v0.1-q8_0", - "7.2\u202fGB" - ], - [ - "7b-v0.2-fp16", - "13\u202fGB" - ], - [ - "7b-v0.2-q2_K", - "2.8\u202fGB" - ], - [ - "7b-v0.2-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-v0.2-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-v0.2-q4_0", - "3.8\u202fGB" - ], - [ - "7b-v0.2-q4_1", - "4.2\u202fGB" - ], - [ - "7b-v0.2-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-v0.2-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-v0.2-q5_0", - "4.7\u202fGB" - ], - [ - "7b-v0.2-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-v0.2-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-v0.2-q6_K", - "5.5\u202fGB" - ], - [ - "7b-v0.2-q8_0", - "7.2\u202fGB" - ], - [ - "13b-v0.1-fp16", - "26\u202fGB" - ], - [ - "13b-v0.1-q2_K", - "5.4\u202fGB" - ], - [ - "13b-v0.1-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-v0.1-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-v0.1-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-v0.1-q4_0", - "7.4\u202fGB" - ], - [ - "13b-v0.1-q4_1", - "8.2\u202fGB" - ], - [ - "13b-v0.1-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-v0.1-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-v0.1-q5_0", - "9.0\u202fGB" - ], - [ - "13b-v0.1-q5_1", - "9.8\u202fGB" - ], - [ - "13b-v0.1-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-v0.1-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-v0.1-q6_K", - "11\u202fGB" - ], - [ - "13b-v0.1-q8_0", - "14\u202fGB" - ], - [ - "13b-v0.2-fp16", - "26\u202fGB" - ], - [ - "13b-v0.2-q2_K", - "5.4\u202fGB" - ], - [ - "13b-v0.2-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-v0.2-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-v0.2-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-v0.2-q4_0", - "7.4\u202fGB" - ], - [ - "13b-v0.2-q4_1", - "8.2\u202fGB" - ], - [ - "13b-v0.2-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-v0.2-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-v0.2-q5_0", - "9.0\u202fGB" - ], - [ - "13b-v0.2-q5_1", - "9.8\u202fGB" - ], - [ - "13b-v0.2-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-v0.2-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-v0.2-q6_K", - "11\u202fGB" - ], - [ - "13b-v0.2-q8_0", - "14\u202fGB" - ], - [ - "70b-v0.1-fp16", - "138\u202fGB" - ], - [ - "70b-v0.1-q2_K", - "29\u202fGB" - ], - [ - "70b-v0.1-q3_K_S", - "30\u202fGB" - ], - [ - "70b-v0.1-q3_K_M", - "33\u202fGB" - ], - [ - "70b-v0.1-q3_K_L", - "36\u202fGB" - ], - [ - "70b-v0.1-q4_0", - "39\u202fGB" - ], - [ - "70b-v0.1-q4_1", - "43\u202fGB" - ], - [ - "70b-v0.1-q4_K_S", - "39\u202fGB" - ], - [ - "70b-v0.1-q4_K_M", - "41\u202fGB" - ], - [ - "70b-v0.1-q5_0", - "47\u202fGB" - ], - [ - "70b-v0.1-q5_1", - "52\u202fGB" - ], - [ - "70b-v0.1-q5_K_S", - "47\u202fGB" - ], - [ - "70b-v0.1-q6_K", - "57\u202fGB" - ], - [ - "70b-v0.1-q8_0", - "73\u202fGB" - ] - ], - "image": false, - "author": "Xwin LM" - }, "sqlcoder": { "url": "https://ollama.com/library/sqlcoder", "description": "SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks", @@ -17343,154 +18467,6 @@ "image": false, "author": "Cognitive Computations" }, - "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", - "4.7\u202fGB" - ], - [ - "8b", - "4.7\u202fGB" - ], - [ - "70b", - "40\u202fGB" - ], - [ - "8b-v1.5", - "4.7\u202fGB" - ], - [ - "70b-v1.5", - "40\u202fGB" - ], - [ - "8b-v1.5-fp16", - "16\u202fGB" - ], - [ - "8b-v1.5-q2_K", - "3.2\u202fGB" - ], - [ - "8b-v1.5-q3_K_S", - "3.7\u202fGB" - ], - [ - "8b-v1.5-q3_K_M", - "4.0\u202fGB" - ], - [ - "8b-v1.5-q3_K_L", - "4.3\u202fGB" - ], - [ - "8b-v1.5-q4_0", - "4.7\u202fGB" - ], - [ - "8b-v1.5-q4_1", - "5.1\u202fGB" - ], - [ - "8b-v1.5-q4_K_S", - "4.7\u202fGB" - ], - [ - "8b-v1.5-q4_K_M", - "4.9\u202fGB" - ], - [ - "8b-v1.5-q5_0", - "5.6\u202fGB" - ], - [ - "8b-v1.5-q5_1", - "6.1\u202fGB" - ], - [ - "8b-v1.5-q5_K_S", - "5.6\u202fGB" - ], - [ - "8b-v1.5-q5_K_M", - "5.7\u202fGB" - ], - [ - "8b-v1.5-q6_K", - "6.6\u202fGB" - ], - [ - "8b-v1.5-q8_0", - "8.5\u202fGB" - ], - [ - "70b-v1.5-fp16", - "141\u202fGB" - ], - [ - "70b-v1.5-q2_K", - "26\u202fGB" - ], - [ - "70b-v1.5-q3_K_S", - "31\u202fGB" - ], - [ - "70b-v1.5-q3_K_M", - "34\u202fGB" - ], - [ - "70b-v1.5-q3_K_L", - "37\u202fGB" - ], - [ - "70b-v1.5-q4_0", - "40\u202fGB" - ], - [ - "70b-v1.5-q4_1", - "44\u202fGB" - ], - [ - "70b-v1.5-q4_K_S", - "40\u202fGB" - ], - [ - "70b-v1.5-q4_K_M", - "43\u202fGB" - ], - [ - "70b-v1.5-q5_0", - "49\u202fGB" - ], - [ - "70b-v1.5-q5_1", - "53\u202fGB" - ], - [ - "70b-v1.5-q5_K_S", - "49\u202fGB" - ], - [ - "70b-v1.5-q5_K_M", - "50\u202fGB" - ], - [ - "70b-v1.5-q6_K", - "58\u202fGB" - ], - [ - "70b-v1.5-q8_0", - "75\u202fGB" - ] - ], - "image": false, - "author": "Nvidia" - }, "yarn-llama2": { "url": "https://ollama.com/library/yarn-llama2", "description": "An extension of Llama 2 that supports a context of up to 128k tokens.", @@ -17767,382 +18743,6 @@ "image": false, "author": "Nous Research" }, - "mistral-large": { - "url": "https://ollama.com/library/mistral-large", - "description": "Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.", - "tags": [ - [ - "latest", - "69\u202fGB" - ], - [ - "123b", - "69\u202fGB" - ], - [ - "123b-instruct-2407-fp16", - "245\u202fGB" - ], - [ - "123b-instruct-2407-q2_K", - "45\u202fGB" - ], - [ - "123b-instruct-2407-q3_K_S", - "53\u202fGB" - ], - [ - "123b-instruct-2407-q3_K_M", - "59\u202fGB" - ], - [ - "123b-instruct-2407-q3_K_L", - "65\u202fGB" - ], - [ - "123b-instruct-2407-q4_0", - "69\u202fGB" - ], - [ - "123b-instruct-2407-q4_1", - "77\u202fGB" - ], - [ - "123b-instruct-2407-q4_K_S", - "70\u202fGB" - ], - [ - "123b-instruct-2407-q4_K_M", - "73\u202fGB" - ], - [ - "123b-instruct-2407-q5_0", - "84\u202fGB" - ], - [ - "123b-instruct-2407-q5_1", - "92\u202fGB" - ], - [ - "123b-instruct-2407-q5_K_S", - "84\u202fGB" - ], - [ - "123b-instruct-2407-q5_K_M", - "86\u202fGB" - ], - [ - "123b-instruct-2407-q6_K", - "101\u202fGB" - ], - [ - "123b-instruct-2407-q8_0", - "130\u202fGB" - ] - ], - "image": false, - "author": "Mistral AI" - }, - "wizardlm": { - "url": "https://ollama.com/library/wizardlm", - "description": "General use model based on Llama 2.", - "tags": [ - [ - "7b-fp16", - "13\u202fGB" - ], - [ - "7b-q2_K", - "2.8\u202fGB" - ], - [ - "7b-q3_K_S", - "2.9\u202fGB" - ], - [ - "7b-q3_K_M", - "3.3\u202fGB" - ], - [ - "7b-q3_K_L", - "3.6\u202fGB" - ], - [ - "7b-q4_0", - "3.8\u202fGB" - ], - [ - "7b-q4_1", - "4.2\u202fGB" - ], - [ - "7b-q4_K_S", - "3.9\u202fGB" - ], - [ - "7b-q4_K_M", - "4.1\u202fGB" - ], - [ - "7b-q5_0", - "4.7\u202fGB" - ], - [ - "7b-q5_1", - "5.1\u202fGB" - ], - [ - "7b-q5_K_S", - "4.7\u202fGB" - ], - [ - "7b-q5_K_M", - "4.8\u202fGB" - ], - [ - "7b-q6_K", - "5.5\u202fGB" - ], - [ - "7b-q8_0", - "7.2\u202fGB" - ], - [ - "13b-fp16", - "26\u202fGB" - ], - [ - "13b-q2_K", - "5.4\u202fGB" - ], - [ - "13b-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-q4_0", - "7.4\u202fGB" - ], - [ - "13b-q4_1", - "8.2\u202fGB" - ], - [ - "13b-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-q5_0", - "9.0\u202fGB" - ], - [ - "13b-q5_1", - "9.8\u202fGB" - ], - [ - "13b-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-q6_K", - "11\u202fGB" - ], - [ - "13b-q8_0", - "14\u202fGB" - ], - [ - "30b-fp16", - "65\u202fGB" - ], - [ - "30b-q2_K", - "14\u202fGB" - ], - [ - "30b-q3_K_S", - "14\u202fGB" - ], - [ - "30b-q3_K_M", - "16\u202fGB" - ], - [ - "30b-q3_K_L", - "17\u202fGB" - ], - [ - "30b-q4_0", - "18\u202fGB" - ], - [ - "30b-q4_1", - "20\u202fGB" - ], - [ - "30b-q4_K_S", - "18\u202fGB" - ], - [ - "30b-q4_K_M", - "20\u202fGB" - ], - [ - "30b-q5_0", - "22\u202fGB" - ], - [ - "30b-q5_1", - "24\u202fGB" - ], - [ - "30b-q5_K_S", - "22\u202fGB" - ], - [ - "30b-q5_K_M", - "23\u202fGB" - ], - [ - "30b-q6_K", - "27\u202fGB" - ], - [ - "30b-q8_0", - "35\u202fGB" - ], - [ - "13b-llama2-fp16", - "26\u202fGB" - ], - [ - "13b-llama2-q2_K", - "5.4\u202fGB" - ], - [ - "13b-llama2-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-llama2-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-llama2-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-llama2-q4_0", - "7.4\u202fGB" - ], - [ - "13b-llama2-q4_1", - "8.2\u202fGB" - ], - [ - "13b-llama2-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-llama2-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-llama2-q5_0", - "9.0\u202fGB" - ], - [ - "13b-llama2-q5_1", - "9.8\u202fGB" - ], - [ - "13b-llama2-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-llama2-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-llama2-q6_K", - "11\u202fGB" - ], - [ - "13b-llama2-q8_0", - "14\u202fGB" - ], - [ - "70b-llama2-q2_K", - "29\u202fGB" - ], - [ - "70b-llama2-q3_K_S", - "30\u202fGB" - ], - [ - "70b-llama2-q3_K_M", - "33\u202fGB" - ], - [ - "70b-llama2-q3_K_L", - "36\u202fGB" - ], - [ - "70b-llama2-q4_0", - "39\u202fGB" - ], - [ - "70b-llama2-q4_1", - "43\u202fGB" - ], - [ - "70b-llama2-q4_K_S", - "39\u202fGB" - ], - [ - "70b-llama2-q4_K_M", - "41\u202fGB" - ], - [ - "70b-llama2-q5_0", - "47\u202fGB" - ], - [ - "70b-llama2-q5_K_S", - "47\u202fGB" - ], - [ - "70b-llama2-q5_K_M", - "49\u202fGB" - ], - [ - "70b-llama2-q6_K", - "57\u202fGB" - ], - [ - "70b-llama2-q8_0", - "73\u202fGB" - ] - ], - "image": false, - "author": "WizardLM Team" - }, "smollm": { "url": "https://ollama.com/library/smollm", "description": "\ud83e\ude90 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.", @@ -18525,7 +19125,451 @@ ] ], "image": false, - "author": "HuggingFaceTB" + "author": "Hugging Face TB" + }, + "wizardlm": { + "url": "https://ollama.com/library/wizardlm", + "description": "General use model based on Llama 2.", + "tags": [ + [ + "7b-fp16", + "13\u202fGB" + ], + [ + "7b-q2_K", + "2.8\u202fGB" + ], + [ + "7b-q3_K_S", + "2.9\u202fGB" + ], + [ + "7b-q3_K_M", + "3.3\u202fGB" + ], + [ + "7b-q3_K_L", + "3.6\u202fGB" + ], + [ + "7b-q4_0", + "3.8\u202fGB" + ], + [ + "7b-q4_1", + "4.2\u202fGB" + ], + [ + "7b-q4_K_S", + "3.9\u202fGB" + ], + [ + "7b-q4_K_M", + "4.1\u202fGB" + ], + [ + "7b-q5_0", + "4.7\u202fGB" + ], + [ + "7b-q5_1", + "5.1\u202fGB" + ], + [ + "7b-q5_K_S", + "4.7\u202fGB" + ], + [ + "7b-q5_K_M", + "4.8\u202fGB" + ], + [ + "7b-q6_K", + "5.5\u202fGB" + ], + [ + "7b-q8_0", + "7.2\u202fGB" + ], + [ + "13b-fp16", + "26\u202fGB" + ], + [ + "13b-q2_K", + "5.4\u202fGB" + ], + [ + "13b-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-q4_0", + "7.4\u202fGB" + ], + [ + "13b-q4_1", + "8.2\u202fGB" + ], + [ + "13b-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-q5_0", + "9.0\u202fGB" + ], + [ + "13b-q5_1", + "9.8\u202fGB" + ], + [ + "13b-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-q6_K", + "11\u202fGB" + ], + [ + "13b-q8_0", + "14\u202fGB" + ], + [ + "30b-fp16", + "65\u202fGB" + ], + [ + "30b-q2_K", + "14\u202fGB" + ], + [ + "30b-q3_K_S", + "14\u202fGB" + ], + [ + "30b-q3_K_M", + "16\u202fGB" + ], + [ + "30b-q3_K_L", + "17\u202fGB" + ], + [ + "30b-q4_0", + "18\u202fGB" + ], + [ + "30b-q4_1", + "20\u202fGB" + ], + [ + "30b-q4_K_S", + "18\u202fGB" + ], + [ + "30b-q4_K_M", + "20\u202fGB" + ], + [ + "30b-q5_0", + "22\u202fGB" + ], + [ + "30b-q5_1", + "24\u202fGB" + ], + [ + "30b-q5_K_S", + "22\u202fGB" + ], + [ + "30b-q5_K_M", + "23\u202fGB" + ], + [ + "30b-q6_K", + "27\u202fGB" + ], + [ + "30b-q8_0", + "35\u202fGB" + ], + [ + "13b-llama2-fp16", + "26\u202fGB" + ], + [ + "13b-llama2-q2_K", + "5.4\u202fGB" + ], + [ + "13b-llama2-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-llama2-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-llama2-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-llama2-q4_0", + "7.4\u202fGB" + ], + [ + "13b-llama2-q4_1", + "8.2\u202fGB" + ], + [ + "13b-llama2-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-llama2-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-llama2-q5_0", + "9.0\u202fGB" + ], + [ + "13b-llama2-q5_1", + "9.8\u202fGB" + ], + [ + "13b-llama2-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-llama2-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-llama2-q6_K", + "11\u202fGB" + ], + [ + "13b-llama2-q8_0", + "14\u202fGB" + ], + [ + "70b-llama2-q2_K", + "29\u202fGB" + ], + [ + "70b-llama2-q3_K_S", + "30\u202fGB" + ], + [ + "70b-llama2-q3_K_M", + "33\u202fGB" + ], + [ + "70b-llama2-q3_K_L", + "36\u202fGB" + ], + [ + "70b-llama2-q4_0", + "39\u202fGB" + ], + [ + "70b-llama2-q4_1", + "43\u202fGB" + ], + [ + "70b-llama2-q4_K_S", + "39\u202fGB" + ], + [ + "70b-llama2-q4_K_M", + "41\u202fGB" + ], + [ + "70b-llama2-q5_0", + "47\u202fGB" + ], + [ + "70b-llama2-q5_K_S", + "47\u202fGB" + ], + [ + "70b-llama2-q5_K_M", + "49\u202fGB" + ], + [ + "70b-llama2-q6_K", + "57\u202fGB" + ], + [ + "70b-llama2-q8_0", + "73\u202fGB" + ] + ], + "image": false, + "author": "WizardLM Team" + }, + "deepseek-v2": { + "url": "https://ollama.com/library/deepseek-v2", + "description": "A strong, economical, and efficient Mixture-of-Experts language model.", + "tags": [ + [ + "latest", + "8.9\u202fGB" + ], + [ + "16b", + "8.9\u202fGB" + ], + [ + "236b", + "133\u202fGB" + ], + [ + "lite", + "8.9\u202fGB" + ], + [ + "16b-lite-chat-fp16", + "31\u202fGB" + ], + [ + "16b-lite-chat-q2_K", + "6.4\u202fGB" + ], + [ + "16b-lite-chat-q3_K_S", + "7.5\u202fGB" + ], + [ + "16b-lite-chat-q3_K_M", + "8.1\u202fGB" + ], + [ + "16b-lite-chat-q3_K_L", + "8.5\u202fGB" + ], + [ + "16b-lite-chat-q4_0", + "8.9\u202fGB" + ], + [ + "16b-lite-chat-q4_1", + "9.9\u202fGB" + ], + [ + "16b-lite-chat-q4_K_S", + "9.5\u202fGB" + ], + [ + "16b-lite-chat-q4_K_M", + "10\u202fGB" + ], + [ + "16b-lite-chat-q5_0", + "11\u202fGB" + ], + [ + "16b-lite-chat-q5_1", + "12\u202fGB" + ], + [ + "16b-lite-chat-q5_K_S", + "11\u202fGB" + ], + [ + "16b-lite-chat-q5_K_M", + "12\u202fGB" + ], + [ + "16b-lite-chat-q6_K", + "14\u202fGB" + ], + [ + "16b-lite-chat-q8_0", + "17\u202fGB" + ], + [ + "236b-chat-fp16", + "472\u202fGB" + ], + [ + "236b-chat-q2_K", + "86\u202fGB" + ], + [ + "236b-chat-q3_K_S", + "102\u202fGB" + ], + [ + "236b-chat-q3_K_M", + "113\u202fGB" + ], + [ + "236b-chat-q3_K_L", + "122\u202fGB" + ], + [ + "236b-chat-q4_0", + "133\u202fGB" + ], + [ + "236b-chat-q4_1", + "148\u202fGB" + ], + [ + "236b-chat-q4_K_S", + "134\u202fGB" + ], + [ + "236b-chat-q4_K_M", + "142\u202fGB" + ], + [ + "236b-chat-q5_0", + "162\u202fGB" + ], + [ + "236b-chat-q5_1", + "177\u202fGB" + ], + [ + "236b-chat-q5_K_S", + "162\u202fGB" + ], + [ + "236b-chat-q5_K_M", + "167\u202fGB" + ], + [ + "236b-chat-q6_K", + "194\u202fGB" + ], + [ + "236b-chat-q8_0", + "251\u202fGB" + ] + ], + "image": false, + "author": "DeepSeek Team" }, "starling-lm": { "url": "https://ollama.com/library/starling-lm", @@ -18679,234 +19723,6 @@ "image": false, "author": "Berkeley Nest" }, - "reflection": { - "url": "https://ollama.com/library/reflection", - "description": "A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.", - "tags": [ - [ - "latest", - "40\u202fGB" - ], - [ - "70b", - "40\u202fGB" - ], - [ - "70b-fp16", - "141\u202fGB" - ], - [ - "70b-q2_K", - "26\u202fGB" - ], - [ - "70b-q3_K_S", - "31\u202fGB" - ], - [ - "70b-q3_K_M", - "34\u202fGB" - ], - [ - "70b-q3_K_L", - "37\u202fGB" - ], - [ - "70b-q4_0", - "40\u202fGB" - ], - [ - "70b-q4_1", - "44\u202fGB" - ], - [ - "70b-q4_K_S", - "40\u202fGB" - ], - [ - "70b-q4_K_M", - "43\u202fGB" - ], - [ - "70b-q5_0", - "49\u202fGB" - ], - [ - "70b-q5_1", - "53\u202fGB" - ], - [ - "70b-q5_K_S", - "49\u202fGB" - ], - [ - "70b-q5_K_M", - "50\u202fGB" - ], - [ - "70b-q6_K", - "58\u202fGB" - ], - [ - "70b-q8_0", - "75\u202fGB" - ] - ], - "image": false, - "author": "Mattshumer" - }, - "moondream": { - "url": "https://ollama.com/library/moondream", - "description": "moondream2 is a small vision language model designed to run efficiently on edge devices.", - "tags": [ - [ - "latest", - "1.7\u202fGB" - ], - [ - "1.8b", - "1.7\u202fGB" - ], - [ - "v2", - "1.7\u202fGB" - ], - [ - "1.8b-v2-fp16", - "3.7\u202fGB" - ], - [ - "1.8b-v2-q2_K", - "1.5\u202fGB" - ], - [ - "1.8b-v2-q3_K_S", - "1.6\u202fGB" - ], - [ - "1.8b-v2-q3_K_M", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q3_K_L", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q4_0", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q4_1", - "1.8\u202fGB" - ], - [ - "1.8b-v2-q4_K_S", - "1.7\u202fGB" - ], - [ - "1.8b-v2-q4_K_M", - "1.8\u202fGB" - ], - [ - "1.8b-v2-q5_0", - "1.9\u202fGB" - ], - [ - "1.8b-v2-q5_1", - "2.0\u202fGB" - ], - [ - "1.8b-v2-q5_K_S", - "1.9\u202fGB" - ], - [ - "1.8b-v2-q5_K_M", - "2.0\u202fGB" - ], - [ - "1.8b-v2-q6_K", - "2.1\u202fGB" - ], - [ - "1.8b-v2-q8_0", - "2.4\u202fGB" - ] - ], - "image": true, - "author": "Vikhyatk" - }, - "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", - "669\u202fMB" - ], - [ - "22m", - "46\u202fMB" - ], - [ - "33m", - "67\u202fMB" - ], - [ - "110m", - "219\u202fMB" - ], - [ - "137m", - "274\u202fMB" - ], - [ - "335m", - "669\u202fMB" - ], - [ - "l", - "669\u202fMB" - ], - [ - "m", - "219\u202fMB" - ], - [ - "m-long", - "274\u202fMB" - ], - [ - "s", - "67\u202fMB" - ], - [ - "xs", - "46\u202fMB" - ], - [ - "22m-xs-fp16", - "46\u202fMB" - ], - [ - "33m-s-fp16", - "67\u202fMB" - ], - [ - "110m-m-fp16", - "219\u202fMB" - ], - [ - "137m-m-long-fp16", - "274\u202fMB" - ], - [ - "335m-l-fp16", - "669\u202fMB" - ] - ], - "image": false, - "author": "Snowflake" - }, "samantha-mistral": { "url": "https://ollama.com/library/samantha-mistral", "description": "A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.", @@ -19387,150 +20203,6 @@ "image": false, "author": "Microsoft Research" }, - "deepseek-v2": { - "url": "https://ollama.com/library/deepseek-v2", - "description": "A strong, economical, and efficient Mixture-of-Experts language model.", - "tags": [ - [ - "latest", - "8.9\u202fGB" - ], - [ - "16b", - "8.9\u202fGB" - ], - [ - "236b", - "133\u202fGB" - ], - [ - "lite", - "8.9\u202fGB" - ], - [ - "16b-lite-chat-fp16", - "31\u202fGB" - ], - [ - "16b-lite-chat-q2_K", - "6.4\u202fGB" - ], - [ - "16b-lite-chat-q3_K_S", - "7.5\u202fGB" - ], - [ - "16b-lite-chat-q3_K_M", - "8.1\u202fGB" - ], - [ - "16b-lite-chat-q3_K_L", - "8.5\u202fGB" - ], - [ - "16b-lite-chat-q4_0", - "8.9\u202fGB" - ], - [ - "16b-lite-chat-q4_1", - "9.9\u202fGB" - ], - [ - "16b-lite-chat-q4_K_S", - "9.5\u202fGB" - ], - [ - "16b-lite-chat-q4_K_M", - "10\u202fGB" - ], - [ - "16b-lite-chat-q5_0", - "11\u202fGB" - ], - [ - "16b-lite-chat-q5_1", - "12\u202fGB" - ], - [ - "16b-lite-chat-q5_K_S", - "11\u202fGB" - ], - [ - "16b-lite-chat-q5_K_M", - "12\u202fGB" - ], - [ - "16b-lite-chat-q6_K", - "14\u202fGB" - ], - [ - "16b-lite-chat-q8_0", - "17\u202fGB" - ], - [ - "236b-chat-fp16", - "472\u202fGB" - ], - [ - "236b-chat-q2_K", - "86\u202fGB" - ], - [ - "236b-chat-q3_K_S", - "102\u202fGB" - ], - [ - "236b-chat-q3_K_M", - "113\u202fGB" - ], - [ - "236b-chat-q3_K_L", - "122\u202fGB" - ], - [ - "236b-chat-q4_0", - "133\u202fGB" - ], - [ - "236b-chat-q4_1", - "148\u202fGB" - ], - [ - "236b-chat-q4_K_S", - "134\u202fGB" - ], - [ - "236b-chat-q4_K_M", - "142\u202fGB" - ], - [ - "236b-chat-q5_0", - "162\u202fGB" - ], - [ - "236b-chat-q5_1", - "177\u202fGB" - ], - [ - "236b-chat-q5_K_S", - "162\u202fGB" - ], - [ - "236b-chat-q5_K_M", - "167\u202fGB" - ], - [ - "236b-chat-q6_K", - "194\u202fGB" - ], - [ - "236b-chat-q8_0", - "251\u202fGB" - ] - ], - "image": false, - "author": "DeepSeek Team" - }, "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.", @@ -19735,142 +20407,6 @@ "image": false, "author": "Stability AI" }, - "glm4": { - "url": "https://ollama.com/library/glm4", - "description": "A strong multi-lingual general language model with competitive performance to Llama 3.", - "tags": [ - [ - "latest", - "5.5\u202fGB" - ], - [ - "9b", - "5.5\u202fGB" - ], - [ - "9b-chat-fp16", - "19\u202fGB" - ], - [ - "9b-chat-q2_K", - "4.0\u202fGB" - ], - [ - "9b-chat-q3_K_S", - "4.6\u202fGB" - ], - [ - "9b-chat-q3_K_M", - "5.1\u202fGB" - ], - [ - "9b-chat-q3_K_L", - "5.3\u202fGB" - ], - [ - "9b-chat-q4_0", - "5.5\u202fGB" - ], - [ - "9b-chat-q4_1", - "6.0\u202fGB" - ], - [ - "9b-chat-q4_K_S", - "5.8\u202fGB" - ], - [ - "9b-chat-q4_K_M", - "6.3\u202fGB" - ], - [ - "9b-chat-q5_0", - "6.6\u202fGB" - ], - [ - "9b-chat-q5_1", - "7.1\u202fGB" - ], - [ - "9b-chat-q5_K_S", - "6.7\u202fGB" - ], - [ - "9b-chat-q5_K_M", - "7.1\u202fGB" - ], - [ - "9b-chat-q6_K", - "8.3\u202fGB" - ], - [ - "9b-chat-q8_0", - "10.0\u202fGB" - ], - [ - "9b-text-fp16", - "19\u202fGB" - ], - [ - "9b-text-q2_K", - "4.0\u202fGB" - ], - [ - "9b-text-q3_K_S", - "4.6\u202fGB" - ], - [ - "9b-text-q3_K_M", - "5.1\u202fGB" - ], - [ - "9b-text-q3_K_L", - "5.3\u202fGB" - ], - [ - "9b-text-q4_0", - "5.5\u202fGB" - ], - [ - "9b-text-q4_1", - "6.0\u202fGB" - ], - [ - "9b-text-q4_K_S", - "5.8\u202fGB" - ], - [ - "9b-text-q4_K_M", - "6.3\u202fGB" - ], - [ - "9b-text-q5_0", - "6.6\u202fGB" - ], - [ - "9b-text-q5_1", - "7.1\u202fGB" - ], - [ - "9b-text-q5_K_S", - "6.7\u202fGB" - ], - [ - "9b-text-q5_K_M", - "7.1\u202fGB" - ], - [ - "9b-text-q6_K", - "8.3\u202fGB" - ], - [ - "9b-text-q8_0", - "10.0\u202fGB" - ] - ], - "image": false, - "author": "THUDM" - }, "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.", @@ -20019,30 +20555,6 @@ "image": false, "author": "TheBloke AI" }, - "llava-phi3": { - "url": "https://ollama.com/library/llava-phi3", - "description": "A new small LLaVA model fine-tuned from Phi 3 Mini.", - "tags": [ - [ - "latest", - "2.9\u202fGB" - ], - [ - "3.8b", - "2.9\u202fGB" - ], - [ - "3.8b-mini-fp16", - "8.3\u202fGB" - ], - [ - "3.8b-mini-q4_0", - "2.9\u202fGB" - ] - ], - "image": false, - "author": "Xtuner" - }, "hermes3": { "url": "https://ollama.com/library/hermes3", "description": "Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research", @@ -20245,7 +20757,575 @@ ] ], "image": false, - "author": "NousResearch" + "author": "Nous Research" + }, + "yi-coder": { + "url": "https://ollama.com/library/yi-coder", + "description": "Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.", + "tags": [ + [ + "latest", + "5.0\u202fGB" + ], + [ + "1.5b", + "866\u202fMB" + ], + [ + "9b", + "5.0\u202fGB" + ], + [ + "1.5b-base", + "866\u202fMB" + ], + [ + "1.5b-chat", + "866\u202fMB" + ], + [ + "9b-base", + "5.0\u202fGB" + ], + [ + "9b-chat", + "5.0\u202fGB" + ], + [ + "1.5b-base-fp16", + "3.0\u202fGB" + ], + [ + "1.5b-base-q2_K", + "635\u202fMB" + ], + [ + "1.5b-base-q3_K_S", + "723\u202fMB" + ], + [ + "1.5b-base-q3_K_M", + "786\u202fMB" + ], + [ + "1.5b-base-q3_K_L", + "826\u202fMB" + ], + [ + "1.5b-base-q4_0", + "866\u202fMB" + ], + [ + "1.5b-base-q4_1", + "950\u202fMB" + ], + [ + "1.5b-base-q4_K_S", + "904\u202fMB" + ], + [ + "1.5b-base-q4_K_M", + "964\u202fMB" + ], + [ + "1.5b-base-q5_0", + "1.0\u202fGB" + ], + [ + "1.5b-base-q5_1", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-base-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-base-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-base-q8_0", + "1.6\u202fGB" + ], + [ + "1.5b-chat-fp16", + "3.0\u202fGB" + ], + [ + "1.5b-chat-q2_K", + "635\u202fMB" + ], + [ + "1.5b-chat-q3_K_S", + "723\u202fMB" + ], + [ + "1.5b-chat-q3_K_M", + "786\u202fMB" + ], + [ + "1.5b-chat-q3_K_L", + "826\u202fMB" + ], + [ + "1.5b-chat-q4_0", + "866\u202fMB" + ], + [ + "1.5b-chat-q4_1", + "950\u202fMB" + ], + [ + "1.5b-chat-q4_K_S", + "904\u202fMB" + ], + [ + "1.5b-chat-q4_K_M", + "964\u202fMB" + ], + [ + "1.5b-chat-q5_0", + "1.0\u202fGB" + ], + [ + "1.5b-chat-q5_1", + "1.1\u202fGB" + ], + [ + "1.5b-chat-q5_K_S", + "1.1\u202fGB" + ], + [ + "1.5b-chat-q5_K_M", + "1.1\u202fGB" + ], + [ + "1.5b-chat-q6_K", + "1.3\u202fGB" + ], + [ + "1.5b-chat-q8_0", + "1.6\u202fGB" + ], + [ + "9b-base-fp16", + "18\u202fGB" + ], + [ + "9b-base-q2_K", + "3.4\u202fGB" + ], + [ + "9b-base-q3_K_S", + "3.9\u202fGB" + ], + [ + "9b-base-q3_K_M", + "4.3\u202fGB" + ], + [ + "9b-base-q3_K_L", + "4.7\u202fGB" + ], + [ + "9b-base-q4_0", + "5.0\u202fGB" + ], + [ + "9b-base-q4_1", + "5.6\u202fGB" + ], + [ + "9b-base-q4_K_S", + "5.1\u202fGB" + ], + [ + "9b-base-q4_K_M", + "5.3\u202fGB" + ], + [ + "9b-base-q5_0", + "6.1\u202fGB" + ], + [ + "9b-base-q5_1", + "6.6\u202fGB" + ], + [ + "9b-base-q5_K_S", + "6.1\u202fGB" + ], + [ + "9b-base-q5_K_M", + "6.3\u202fGB" + ], + [ + "9b-base-q6_K", + "7.2\u202fGB" + ], + [ + "9b-base-q8_0", + "9.4\u202fGB" + ], + [ + "9b-chat-fp16", + "18\u202fGB" + ], + [ + "9b-chat-q2_K", + "3.4\u202fGB" + ], + [ + "9b-chat-q3_K_S", + "3.9\u202fGB" + ], + [ + "9b-chat-q3_K_M", + "4.3\u202fGB" + ], + [ + "9b-chat-q3_K_L", + "4.7\u202fGB" + ], + [ + "9b-chat-q4_0", + "5.0\u202fGB" + ], + [ + "9b-chat-q4_1", + "5.6\u202fGB" + ], + [ + "9b-chat-q4_K_S", + "5.1\u202fGB" + ], + [ + "9b-chat-q4_K_M", + "5.3\u202fGB" + ], + [ + "9b-chat-q5_0", + "6.1\u202fGB" + ], + [ + "9b-chat-q5_1", + "6.6\u202fGB" + ], + [ + "9b-chat-q5_K_S", + "6.1\u202fGB" + ], + [ + "9b-chat-q5_K_M", + "6.3\u202fGB" + ], + [ + "9b-chat-q6_K", + "7.2\u202fGB" + ], + [ + "9b-chat-q8_0", + "9.4\u202fGB" + ] + ], + "image": false, + "author": "01.AI" + }, + "llava-phi3": { + "url": "https://ollama.com/library/llava-phi3", + "description": "A new small LLaVA model fine-tuned from Phi 3 Mini.", + "tags": [ + [ + "latest", + "2.9\u202fGB" + ], + [ + "3.8b", + "2.9\u202fGB" + ], + [ + "3.8b-mini-fp16", + "8.3\u202fGB" + ], + [ + "3.8b-mini-q4_0", + "2.9\u202fGB" + ] + ], + "image": false, + "author": "Xtuner" + }, + "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", + "4.5\u202fGB" + ], + [ + "1m", + "4.5\u202fGB" + ], + [ + "1.8b", + "1.1\u202fGB" + ], + [ + "7b", + "4.5\u202fGB" + ], + [ + "20b", + "11\u202fGB" + ], + [ + "1.8b-chat-v2.5-fp16", + "3.8\u202fGB" + ], + [ + "1.8b-chat-v2.5-q2_K", + "772\u202fMB" + ], + [ + "1.8b-chat-v2.5-q3_K_S", + "888\u202fMB" + ], + [ + "1.8b-chat-v2.5-q3_K_M", + "964\u202fMB" + ], + [ + "1.8b-chat-v2.5-q3_K_L", + "1.0\u202fGB" + ], + [ + "1.8b-chat-v2.5-q4_0", + "1.1\u202fGB" + ], + [ + "1.8b-chat-v2.5-q4_1", + "1.2\u202fGB" + ], + [ + "1.8b-chat-v2.5-q4_K_S", + "1.1\u202fGB" + ], + [ + "1.8b-chat-v2.5-q4_K_M", + "1.2\u202fGB" + ], + [ + "1.8b-chat-v2.5-q5_0", + "1.3\u202fGB" + ], + [ + "1.8b-chat-v2.5-q5_1", + "1.4\u202fGB" + ], + [ + "1.8b-chat-v2.5-q5_K_S", + "1.3\u202fGB" + ], + [ + "1.8b-chat-v2.5-q5_K_M", + "1.4\u202fGB" + ], + [ + "1.8b-chat-v2.5-q6_K", + "1.6\u202fGB" + ], + [ + "1.8b-chat-v2.5-q8_0", + "2.0\u202fGB" + ], + [ + "7b-chat-1m-v2.5-fp16", + "15\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q2_K", + "3.0\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q4_0", + "4.5\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q4_1", + "4.9\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q5_0", + "5.4\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q5_1", + "5.8\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q5_K_S", + "5.4\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q5_K_M", + "5.5\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q6_K", + "6.4\u202fGB" + ], + [ + "7b-chat-1m-v2.5-q8_0", + "8.2\u202fGB" + ], + [ + "7b-chat-v2.5-fp16", + "15\u202fGB" + ], + [ + "7b-chat-v2.5-q2_K", + "3.0\u202fGB" + ], + [ + "7b-chat-v2.5-q3_K_S", + "3.5\u202fGB" + ], + [ + "7b-chat-v2.5-q3_K_M", + "3.8\u202fGB" + ], + [ + "7b-chat-v2.5-q3_K_L", + "4.1\u202fGB" + ], + [ + "7b-chat-v2.5-q4_0", + "4.5\u202fGB" + ], + [ + "7b-chat-v2.5-q4_1", + "4.9\u202fGB" + ], + [ + "7b-chat-v2.5-q4_K_S", + "4.5\u202fGB" + ], + [ + "7b-chat-v2.5-q4_K_M", + "4.7\u202fGB" + ], + [ + "7b-chat-v2.5-q5_0", + "5.4\u202fGB" + ], + [ + "7b-chat-v2.5-q5_1", + "5.8\u202fGB" + ], + [ + "7b-chat-v2.5-q5_K_S", + "5.4\u202fGB" + ], + [ + "7b-chat-v2.5-q5_K_M", + "5.5\u202fGB" + ], + [ + "7b-chat-v2.5-q6_K", + "6.4\u202fGB" + ], + [ + "7b-chat-v2.5-q8_0", + "8.2\u202fGB" + ], + [ + "20b-chat-v2.5-fp16", + "40\u202fGB" + ], + [ + "20b-chat-v2.5-q2_K", + "7.5\u202fGB" + ], + [ + "20b-chat-v2.5-q3_K_S", + "8.8\u202fGB" + ], + [ + "20b-chat-v2.5-q3_K_M", + "9.7\u202fGB" + ], + [ + "20b-chat-v2.5-q3_K_L", + "11\u202fGB" + ], + [ + "20b-chat-v2.5-q4_0", + "11\u202fGB" + ], + [ + "20b-chat-v2.5-q4_1", + "13\u202fGB" + ], + [ + "20b-chat-v2.5-q4_K_S", + "11\u202fGB" + ], + [ + "20b-chat-v2.5-q4_K_M", + "12\u202fGB" + ], + [ + "20b-chat-v2.5-q5_0", + "14\u202fGB" + ], + [ + "20b-chat-v2.5-q5_1", + "15\u202fGB" + ], + [ + "20b-chat-v2.5-q5_K_S", + "14\u202fGB" + ], + [ + "20b-chat-v2.5-q5_K_M", + "14\u202fGB" + ], + [ + "20b-chat-v2.5-q6_K", + "16\u202fGB" + ], + [ + "20b-chat-v2.5-q8_0", + "21\u202fGB" + ] + ], + "image": false, + "author": "Intern LM" }, "yarn-mistral": { "url": "https://ollama.com/library/yarn-mistral", @@ -20603,550 +21683,6 @@ "image": false, "author": "Siraj Raval" }, - "yi-coder": { - "url": "https://ollama.com/library/yi-coder", - "description": "Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.", - "tags": [ - [ - "latest", - "5.0\u202fGB" - ], - [ - "1.5b", - "866\u202fMB" - ], - [ - "9b", - "5.0\u202fGB" - ], - [ - "1.5b-base", - "866\u202fMB" - ], - [ - "1.5b-chat", - "866\u202fMB" - ], - [ - "9b-base", - "5.0\u202fGB" - ], - [ - "9b-chat", - "5.0\u202fGB" - ], - [ - "1.5b-base-fp16", - "3.0\u202fGB" - ], - [ - "1.5b-base-q2_K", - "635\u202fMB" - ], - [ - "1.5b-base-q3_K_S", - "723\u202fMB" - ], - [ - "1.5b-base-q3_K_M", - "786\u202fMB" - ], - [ - "1.5b-base-q3_K_L", - "826\u202fMB" - ], - [ - "1.5b-base-q4_0", - "866\u202fMB" - ], - [ - "1.5b-base-q4_1", - "950\u202fMB" - ], - [ - "1.5b-base-q4_K_S", - "904\u202fMB" - ], - [ - "1.5b-base-q4_K_M", - "964\u202fMB" - ], - [ - "1.5b-base-q5_0", - "1.0\u202fGB" - ], - [ - "1.5b-base-q5_1", - "1.1\u202fGB" - ], - [ - "1.5b-base-q5_K_S", - "1.1\u202fGB" - ], - [ - "1.5b-base-q5_K_M", - "1.1\u202fGB" - ], - [ - "1.5b-base-q6_K", - "1.3\u202fGB" - ], - [ - "1.5b-base-q8_0", - "1.6\u202fGB" - ], - [ - "1.5b-chat-fp16", - "3.0\u202fGB" - ], - [ - "1.5b-chat-q2_K", - "635\u202fMB" - ], - [ - "1.5b-chat-q3_K_S", - "723\u202fMB" - ], - [ - "1.5b-chat-q3_K_M", - "786\u202fMB" - ], - [ - "1.5b-chat-q3_K_L", - "826\u202fMB" - ], - [ - "1.5b-chat-q4_0", - "866\u202fMB" - ], - [ - "1.5b-chat-q4_1", - "950\u202fMB" - ], - [ - "1.5b-chat-q4_K_S", - "904\u202fMB" - ], - [ - "1.5b-chat-q4_K_M", - "964\u202fMB" - ], - [ - "1.5b-chat-q5_0", - "1.0\u202fGB" - ], - [ - "1.5b-chat-q5_1", - "1.1\u202fGB" - ], - [ - "1.5b-chat-q5_K_S", - "1.1\u202fGB" - ], - [ - "1.5b-chat-q5_K_M", - "1.1\u202fGB" - ], - [ - "1.5b-chat-q6_K", - "1.3\u202fGB" - ], - [ - "1.5b-chat-q8_0", - "1.6\u202fGB" - ], - [ - "9b-base-fp16", - "18\u202fGB" - ], - [ - "9b-base-q2_K", - "3.4\u202fGB" - ], - [ - "9b-base-q3_K_S", - "3.9\u202fGB" - ], - [ - "9b-base-q3_K_M", - "4.3\u202fGB" - ], - [ - "9b-base-q3_K_L", - "4.7\u202fGB" - ], - [ - "9b-base-q4_0", - "5.0\u202fGB" - ], - [ - "9b-base-q4_1", - "5.6\u202fGB" - ], - [ - "9b-base-q4_K_S", - "5.1\u202fGB" - ], - [ - "9b-base-q4_K_M", - "5.3\u202fGB" - ], - [ - "9b-base-q5_0", - "6.1\u202fGB" - ], - [ - "9b-base-q5_1", - "6.6\u202fGB" - ], - [ - "9b-base-q5_K_S", - "6.1\u202fGB" - ], - [ - "9b-base-q5_K_M", - "6.3\u202fGB" - ], - [ - "9b-base-q6_K", - "7.2\u202fGB" - ], - [ - "9b-base-q8_0", - "9.4\u202fGB" - ], - [ - "9b-chat-fp16", - "18\u202fGB" - ], - [ - "9b-chat-q2_K", - "3.4\u202fGB" - ], - [ - "9b-chat-q3_K_S", - "3.9\u202fGB" - ], - [ - "9b-chat-q3_K_M", - "4.3\u202fGB" - ], - [ - "9b-chat-q3_K_L", - "4.7\u202fGB" - ], - [ - "9b-chat-q4_0", - "5.0\u202fGB" - ], - [ - "9b-chat-q4_1", - "5.6\u202fGB" - ], - [ - "9b-chat-q4_K_S", - "5.1\u202fGB" - ], - [ - "9b-chat-q4_K_M", - "5.3\u202fGB" - ], - [ - "9b-chat-q5_0", - "6.1\u202fGB" - ], - [ - "9b-chat-q5_1", - "6.6\u202fGB" - ], - [ - "9b-chat-q5_K_S", - "6.1\u202fGB" - ], - [ - "9b-chat-q5_K_M", - "6.3\u202fGB" - ], - [ - "9b-chat-q6_K", - "7.2\u202fGB" - ], - [ - "9b-chat-q8_0", - "9.4\u202fGB" - ] - ], - "image": false, - "author": "01-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", - "4.5\u202fGB" - ], - [ - "1m", - "4.5\u202fGB" - ], - [ - "1.8b", - "1.1\u202fGB" - ], - [ - "7b", - "4.5\u202fGB" - ], - [ - "20b", - "11\u202fGB" - ], - [ - "1.8b-chat-v2.5-fp16", - "3.8\u202fGB" - ], - [ - "1.8b-chat-v2.5-q2_K", - "772\u202fMB" - ], - [ - "1.8b-chat-v2.5-q3_K_S", - "888\u202fMB" - ], - [ - "1.8b-chat-v2.5-q3_K_M", - "964\u202fMB" - ], - [ - "1.8b-chat-v2.5-q3_K_L", - "1.0\u202fGB" - ], - [ - "1.8b-chat-v2.5-q4_0", - "1.1\u202fGB" - ], - [ - "1.8b-chat-v2.5-q4_1", - "1.2\u202fGB" - ], - [ - "1.8b-chat-v2.5-q4_K_S", - "1.1\u202fGB" - ], - [ - "1.8b-chat-v2.5-q4_K_M", - "1.2\u202fGB" - ], - [ - "1.8b-chat-v2.5-q5_0", - "1.3\u202fGB" - ], - [ - "1.8b-chat-v2.5-q5_1", - "1.4\u202fGB" - ], - [ - "1.8b-chat-v2.5-q5_K_S", - "1.3\u202fGB" - ], - [ - "1.8b-chat-v2.5-q5_K_M", - "1.4\u202fGB" - ], - [ - "1.8b-chat-v2.5-q6_K", - "1.6\u202fGB" - ], - [ - "1.8b-chat-v2.5-q8_0", - "2.0\u202fGB" - ], - [ - "7b-chat-1m-v2.5-fp16", - "15\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q2_K", - "3.0\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q3_K_L", - "4.1\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q4_0", - "4.5\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q4_1", - "4.9\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q4_K_S", - "4.5\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q4_K_M", - "4.7\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q5_0", - "5.4\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q5_1", - "5.8\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q5_K_S", - "5.4\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q5_K_M", - "5.5\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q6_K", - "6.4\u202fGB" - ], - [ - "7b-chat-1m-v2.5-q8_0", - "8.2\u202fGB" - ], - [ - "7b-chat-v2.5-fp16", - "15\u202fGB" - ], - [ - "7b-chat-v2.5-q2_K", - "3.0\u202fGB" - ], - [ - "7b-chat-v2.5-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-chat-v2.5-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-chat-v2.5-q3_K_L", - "4.1\u202fGB" - ], - [ - "7b-chat-v2.5-q4_0", - "4.5\u202fGB" - ], - [ - "7b-chat-v2.5-q4_1", - "4.9\u202fGB" - ], - [ - "7b-chat-v2.5-q4_K_S", - "4.5\u202fGB" - ], - [ - "7b-chat-v2.5-q4_K_M", - "4.7\u202fGB" - ], - [ - "7b-chat-v2.5-q5_0", - "5.4\u202fGB" - ], - [ - "7b-chat-v2.5-q5_1", - "5.8\u202fGB" - ], - [ - "7b-chat-v2.5-q5_K_S", - "5.4\u202fGB" - ], - [ - "7b-chat-v2.5-q5_K_M", - "5.5\u202fGB" - ], - [ - "7b-chat-v2.5-q6_K", - "6.4\u202fGB" - ], - [ - "7b-chat-v2.5-q8_0", - "8.2\u202fGB" - ], - [ - "20b-chat-v2.5-fp16", - "40\u202fGB" - ], - [ - "20b-chat-v2.5-q2_K", - "7.5\u202fGB" - ], - [ - "20b-chat-v2.5-q3_K_S", - "8.8\u202fGB" - ], - [ - "20b-chat-v2.5-q3_K_M", - "9.7\u202fGB" - ], - [ - "20b-chat-v2.5-q3_K_L", - "11\u202fGB" - ], - [ - "20b-chat-v2.5-q4_0", - "11\u202fGB" - ], - [ - "20b-chat-v2.5-q4_1", - "13\u202fGB" - ], - [ - "20b-chat-v2.5-q4_K_S", - "11\u202fGB" - ], - [ - "20b-chat-v2.5-q4_K_M", - "12\u202fGB" - ], - [ - "20b-chat-v2.5-q5_0", - "14\u202fGB" - ], - [ - "20b-chat-v2.5-q5_1", - "15\u202fGB" - ], - [ - "20b-chat-v2.5-q5_K_S", - "14\u202fGB" - ], - [ - "20b-chat-v2.5-q5_K_M", - "14\u202fGB" - ], - [ - "20b-chat-v2.5-q6_K", - "16\u202fGB" - ], - [ - "20b-chat-v2.5-q8_0", - "21\u202fGB" - ] - ], - "image": false, - "author": "Intern LM" - }, "meditron": { "url": "https://ollama.com/library/meditron", "description": "Open-source medical large language model adapted from Llama 2 to the medical domain.", @@ -21543,86 +22079,6 @@ "image": false, "author": "DeepSE" }, - "everythinglm": { - "url": "https://ollama.com/library/everythinglm", - "description": "Uncensored Llama2 based model with support for a 16K context window.", - "tags": [ - [ - "latest", - "7.4\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "13b-16k", - "7.4\u202fGB" - ], - [ - "13b-16k-fp16", - "26\u202fGB" - ], - [ - "13b-16k-q2_K", - "5.4\u202fGB" - ], - [ - "13b-16k-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-16k-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-16k-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-16k-q4_0", - "7.4\u202fGB" - ], - [ - "13b-16k-q4_1", - "8.2\u202fGB" - ], - [ - "13b-16k-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-16k-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-16k-q5_0", - "9.0\u202fGB" - ], - [ - "13b-16k-q5_1", - "9.8\u202fGB" - ], - [ - "13b-16k-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-16k-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-16k-q6_K", - "11\u202fGB" - ], - [ - "13b-16k-q8_0", - "14\u202fGB" - ] - ], - "image": false, - "author": "Totally Not An LLM" - }, "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.", @@ -21763,6 +22219,86 @@ "image": false, "author": "Groq" }, + "everythinglm": { + "url": "https://ollama.com/library/everythinglm", + "description": "Uncensored Llama2 based model with support for a 16K context window.", + "tags": [ + [ + "latest", + "7.4\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "13b-16k", + "7.4\u202fGB" + ], + [ + "13b-16k-fp16", + "26\u202fGB" + ], + [ + "13b-16k-q2_K", + "5.4\u202fGB" + ], + [ + "13b-16k-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-16k-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-16k-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-16k-q4_0", + "7.4\u202fGB" + ], + [ + "13b-16k-q4_1", + "8.2\u202fGB" + ], + [ + "13b-16k-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-16k-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-16k-q5_0", + "9.0\u202fGB" + ], + [ + "13b-16k-q5_1", + "9.8\u202fGB" + ], + [ + "13b-16k-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-16k-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-16k-q6_K", + "11\u202fGB" + ], + [ + "13b-16k-q8_0", + "14\u202fGB" + ] + ], + "image": false, + "author": "Totally Not An LLM" + }, "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.", @@ -21991,6 +22527,82 @@ "image": false, "author": "Oobabooga" }, + "wizard-vicuna": { + "url": "https://ollama.com/library/wizard-vicuna", + "description": "Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.", + "tags": [ + [ + "latest", + "7.4\u202fGB" + ], + [ + "13b", + "7.4\u202fGB" + ], + [ + "13b-fp16", + "26\u202fGB" + ], + [ + "13b-q2_K", + "5.4\u202fGB" + ], + [ + "13b-q3_K_S", + "5.7\u202fGB" + ], + [ + "13b-q3_K_M", + "6.3\u202fGB" + ], + [ + "13b-q3_K_L", + "6.9\u202fGB" + ], + [ + "13b-q4_0", + "7.4\u202fGB" + ], + [ + "13b-q4_1", + "8.2\u202fGB" + ], + [ + "13b-q4_K_S", + "7.4\u202fGB" + ], + [ + "13b-q4_K_M", + "7.9\u202fGB" + ], + [ + "13b-q5_0", + "9.0\u202fGB" + ], + [ + "13b-q5_1", + "9.8\u202fGB" + ], + [ + "13b-q5_K_S", + "9.0\u202fGB" + ], + [ + "13b-q5_K_M", + "9.2\u202fGB" + ], + [ + "13b-q6_K", + "11\u202fGB" + ], + [ + "13b-q8_0", + "14\u202fGB" + ] + ], + "image": false, + "author": "MelodysDreamj" + }, "mistrallite": { "url": "https://ollama.com/library/mistrallite", "description": "MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.", @@ -22143,82 +22755,6 @@ "image": false, "author": "Technology Innovation Institute" }, - "wizard-vicuna": { - "url": "https://ollama.com/library/wizard-vicuna", - "description": "Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.", - "tags": [ - [ - "latest", - "7.4\u202fGB" - ], - [ - "13b", - "7.4\u202fGB" - ], - [ - "13b-fp16", - "26\u202fGB" - ], - [ - "13b-q2_K", - "5.4\u202fGB" - ], - [ - "13b-q3_K_S", - "5.7\u202fGB" - ], - [ - "13b-q3_K_M", - "6.3\u202fGB" - ], - [ - "13b-q3_K_L", - "6.9\u202fGB" - ], - [ - "13b-q4_0", - "7.4\u202fGB" - ], - [ - "13b-q4_1", - "8.2\u202fGB" - ], - [ - "13b-q4_K_S", - "7.4\u202fGB" - ], - [ - "13b-q4_K_M", - "7.9\u202fGB" - ], - [ - "13b-q5_0", - "9.0\u202fGB" - ], - [ - "13b-q5_1", - "9.8\u202fGB" - ], - [ - "13b-q5_K_S", - "9.0\u202fGB" - ], - [ - "13b-q5_K_M", - "9.2\u202fGB" - ], - [ - "13b-q6_K", - "11\u202fGB" - ], - [ - "13b-q8_0", - "14\u202fGB" - ] - ], - "image": false, - "author": "MelodysDreamj" - }, "duckdb-nsql": { "url": "https://ollama.com/library/duckdb-nsql", "description": "7B parameter text-to-SQL model made by MotherDuck and Numbers Station.", @@ -22295,281 +22831,81 @@ "image": false, "author": "MotherDuck, Numbers Station" }, - "qwen2.5-coder": { - "url": "https://ollama.com/library/qwen2.5-coder", - "description": "The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.", + "minicpm-v": { + "url": "https://ollama.com/library/minicpm-v", + "description": "A series of multimodal LLMs (MLLMs) designed for vision-language understanding.", "tags": [ [ "latest", - "4.7\u202fGB" + "5.5\u202fGB" ], [ - "1.5b", - "986\u202fMB" + "8b", + "5.5\u202fGB" ], [ - "7b", - "4.7\u202fGB" + "8b-2.6-fp16", + "16\u202fGB" ], [ - "1.5b-base", - "986\u202fMB" - ], - [ - "1.5b-instruct", - "986\u202fMB" - ], - [ - "7b-base", - "4.7\u202fGB" - ], - [ - "7b-instruct", - "4.7\u202fGB" - ], - [ - "1.5b-base-fp16", - "3.1\u202fGB" - ], - [ - "1.5b-base-q2_K", - "676\u202fMB" - ], - [ - "1.5b-base-q3_K_S", - "761\u202fMB" - ], - [ - "1.5b-base-q3_K_M", - "824\u202fMB" - ], - [ - "1.5b-base-q3_K_L", - "880\u202fMB" - ], - [ - "1.5b-base-q4_0", - "935\u202fMB" - ], - [ - "1.5b-base-q4_1", - "1.0\u202fGB" - ], - [ - "1.5b-base-q4_K_S", - "940\u202fMB" - ], - [ - "1.5b-base-q4_K_M", - "986\u202fMB" - ], - [ - "1.5b-base-q5_0", - "1.1\u202fGB" - ], - [ - "1.5b-base-q5_1", - "1.2\u202fGB" - ], - [ - "1.5b-base-q5_K_S", - "1.1\u202fGB" - ], - [ - "1.5b-base-q5_K_M", - "1.1\u202fGB" - ], - [ - "1.5b-base-q6_K", - "1.3\u202fGB" - ], - [ - "1.5b-base-q8_0", - "1.6\u202fGB" - ], - [ - "1.5b-instruct-fp16", - "3.1\u202fGB" - ], - [ - "1.5b-instruct-q2_K", - "676\u202fMB" - ], - [ - "1.5b-instruct-q3_K_S", - "761\u202fMB" - ], - [ - "1.5b-instruct-q3_K_M", - "824\u202fMB" - ], - [ - "1.5b-instruct-q3_K_L", - "880\u202fMB" - ], - [ - "1.5b-instruct-q4_0", - "935\u202fMB" - ], - [ - "1.5b-instruct-q4_1", - "1.0\u202fGB" - ], - [ - "1.5b-instruct-q4_K_S", - "940\u202fMB" - ], - [ - "1.5b-instruct-q4_K_M", - "986\u202fMB" - ], - [ - "1.5b-instruct-q5_0", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q5_1", - "1.2\u202fGB" - ], - [ - "1.5b-instruct-q5_K_S", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q5_K_M", - "1.1\u202fGB" - ], - [ - "1.5b-instruct-q6_K", - "1.3\u202fGB" - ], - [ - "1.5b-instruct-q8_0", - "1.6\u202fGB" - ], - [ - "7b-base-fp16", - "15\u202fGB" - ], - [ - "7b-base-q2_K", - "3.0\u202fGB" - ], - [ - "7b-base-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-base-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-base-q3_K_L", + "8b-2.6-q2_K", "4.1\u202fGB" ], [ - "7b-base-q4_0", - "4.4\u202fGB" - ], - [ - "7b-base-q4_1", - "4.9\u202fGB" - ], - [ - "7b-base-q4_K_S", + "8b-2.6-q3_K_S", "4.5\u202fGB" ], [ - "7b-base-q4_K_M", - "4.7\u202fGB" - ], - [ - "7b-base-q5_0", - "5.3\u202fGB" - ], - [ - "7b-base-q5_1", - "5.8\u202fGB" - ], - [ - "7b-base-q5_K_S", - "5.3\u202fGB" - ], - [ - "7b-base-q5_K_M", - "5.4\u202fGB" - ], - [ - "7b-base-q6_K", - "6.3\u202fGB" - ], - [ - "7b-base-q8_0", - "8.1\u202fGB" - ], - [ - "7b-instruct-fp16", - "15\u202fGB" - ], - [ - "7b-instruct-q2_K", - "3.0\u202fGB" - ], - [ - "7b-instruct-q3_K_S", - "3.5\u202fGB" - ], - [ - "7b-instruct-q3_K_M", - "3.8\u202fGB" - ], - [ - "7b-instruct-q3_K_L", - "4.1\u202fGB" - ], - [ - "7b-instruct-q4_0", - "4.4\u202fGB" - ], - [ - "7b-instruct-q4_1", + "8b-2.6-q3_K_M", "4.9\u202fGB" ], [ - "7b-instruct-q4_K_S", - "4.5\u202fGB" + "8b-2.6-q3_K_L", + "5.1\u202fGB" ], [ - "7b-instruct-q4_K_M", - "4.7\u202fGB" + "8b-2.6-q4_0", + "5.5\u202fGB" ], [ - "7b-instruct-q5_0", - "5.3\u202fGB" + "8b-2.6-q4_1", + "5.9\u202fGB" ], [ - "7b-instruct-q5_1", - "5.8\u202fGB" + "8b-2.6-q4_K_S", + "5.5\u202fGB" ], [ - "7b-instruct-q5_K_S", - "5.3\u202fGB" + "8b-2.6-q4_K_M", + "5.7\u202fGB" ], [ - "7b-instruct-q5_K_M", - "5.4\u202fGB" + "8b-2.6-q5_0", + "6.4\u202fGB" ], [ - "7b-instruct-q6_K", - "6.3\u202fGB" + "8b-2.6-q5_1", + "6.8\u202fGB" ], [ - "7b-instruct-q8_0", - "8.1\u202fGB" + "8b-2.6-q5_K_S", + "6.4\u202fGB" + ], + [ + "8b-2.6-q5_K_M", + "6.5\u202fGB" + ], + [ + "8b-2.6-q6_K", + "7.3\u202fGB" + ], + [ + "8b-2.6-q8_0", + "9.1\u202fGB" ] ], "image": false, - "author": "Alibaba" + "author": "OpenBMB" }, "megadolphin": { "url": "https://ollama.com/library/megadolphin", @@ -22981,7 +23317,7 @@ ] ], "image": false, - "author": "Bge M3 Team" + "author": "BGE-m3 Team" }, "mathstral": { "url": "https://ollama.com/library/mathstral", @@ -23095,81 +23431,85 @@ "image": false, "author": "Databricks" }, - "minicpm-v": { - "url": "https://ollama.com/library/minicpm-v", - "description": "A series of multimodal LLMs (MLLMs) designed for vision-language understanding.", + "solar-pro": { + "url": "https://ollama.com/library/solar-pro", + "description": "Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU", "tags": [ [ "latest", - "5.5\u202fGB" + "13\u202fGB" ], [ - "8b", - "5.5\u202fGB" + "22b", + "13\u202fGB" ], [ - "8b-2.6-fp16", + "preview", + "13\u202fGB" + ], + [ + "22b-preview-instruct-fp16", + "44\u202fGB" + ], + [ + "22b-preview-instruct-q2_K", + "8.2\u202fGB" + ], + [ + "22b-preview-instruct-q3_K_S", + "9.6\u202fGB" + ], + [ + "22b-preview-instruct-q3_K_M", + "11\u202fGB" + ], + [ + "22b-preview-instruct-q3_K_L", + "12\u202fGB" + ], + [ + "22b-preview-instruct-q4_0", + "12\u202fGB" + ], + [ + "22b-preview-instruct-q4_1", + "14\u202fGB" + ], + [ + "22b-preview-instruct-q4_K_S", + "13\u202fGB" + ], + [ + "22b-preview-instruct-q4_K_M", + "13\u202fGB" + ], + [ + "22b-preview-instruct-q5_0", + "15\u202fGB" + ], + [ + "22b-preview-instruct-q5_1", + "17\u202fGB" + ], + [ + "22b-preview-instruct-q5_K_S", + "15\u202fGB" + ], + [ + "22b-preview-instruct-q5_K_M", "16\u202fGB" ], [ - "8b-2.6-q2_K", - "4.1\u202fGB" + "22b-preview-instruct-q6_K", + "18\u202fGB" ], [ - "8b-2.6-q3_K_S", - "4.5\u202fGB" - ], - [ - "8b-2.6-q3_K_M", - "4.9\u202fGB" - ], - [ - "8b-2.6-q3_K_L", - "5.1\u202fGB" - ], - [ - "8b-2.6-q4_0", - "5.5\u202fGB" - ], - [ - "8b-2.6-q4_1", - "5.9\u202fGB" - ], - [ - "8b-2.6-q4_K_S", - "5.5\u202fGB" - ], - [ - "8b-2.6-q4_K_M", - "5.7\u202fGB" - ], - [ - "8b-2.6-q5_0", - "6.4\u202fGB" - ], - [ - "8b-2.6-q5_1", - "6.8\u202fGB" - ], - [ - "8b-2.6-q5_K_S", - "6.4\u202fGB" - ], - [ - "8b-2.6-q5_K_M", - "6.5\u202fGB" - ], - [ - "8b-2.6-q6_K", - "7.3\u202fGB" - ], - [ - "8b-2.6-q8_0", - "9.1\u202fGB" + "22b-preview-instruct-q8_0", + "24\u202fGB" ] ], "image": false, - "author": "OpenBMB" + "author": "Upstage" }, "nuextract": { "url": "https://ollama.com/library/nuextract", @@ -23359,106 +23699,6 @@ "image": false, "author": "Fireworks AI" }, - "solar-pro": { - "url": "https://ollama.com/library/solar-pro", - "description": "Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU", - "tags": [ - [ - "latest", - "13\u202fGB" - ], - [ - "22b", - "13\u202fGB" - ], - [ - "preview", - "13\u202fGB" - ], - [ - "22b-preview-instruct-fp16", - "44\u202fGB" - ], - [ - "22b-preview-instruct-q2_K", - "8.2\u202fGB" - ], - [ - "22b-preview-instruct-q3_K_S", - "9.6\u202fGB" - ], - [ - "22b-preview-instruct-q3_K_M", - "11\u202fGB" - ], - [ - "22b-preview-instruct-q3_K_L", - "12\u202fGB" - ], - [ - "22b-preview-instruct-q4_0", - "12\u202fGB" - ], - [ - "22b-preview-instruct-q4_1", - "14\u202fGB" - ], - [ - "22b-preview-instruct-q4_K_S", - "13\u202fGB" - ], - [ - "22b-preview-instruct-q4_K_M", - "13\u202fGB" - ], - [ - "22b-preview-instruct-q5_0", - "15\u202fGB" - ], - [ - "22b-preview-instruct-q5_1", - "17\u202fGB" - ], - [ - "22b-preview-instruct-q5_K_S", - "15\u202fGB" - ], - [ - "22b-preview-instruct-q5_K_M", - "16\u202fGB" - ], - [ - "22b-preview-instruct-q6_K", - "18\u202fGB" - ], - [ - "22b-preview-instruct-q8_0", - "24\u202fGB" - ] - ], - "image": false, - "author": "Upstage" - }, - "bge-large": { - "url": "https://ollama.com/library/bge-large", - "description": "Embedding model from BAAI mapping texts to vectors.", - "tags": [ - [ - "latest", - "671\u202fMB" - ], - [ - "335m", - "671\u202fMB" - ], - [ - "335m-en-v1.5-fp16", - "671\u202fMB" - ] - ], - "image": false, - "author": "Bge Large Team" - }, "reader-lm": { "url": "https://ollama.com/library/reader-lm", "description": "A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.", @@ -23597,7 +23837,27 @@ ] ], "image": false, - "author": "Jina AI" + "author": "JinaAI" + }, + "bge-large": { + "url": "https://ollama.com/library/bge-large", + "description": "Embedding model from BAAI mapping texts to vectors.", + "tags": [ + [ + "latest", + "671\u202fMB" + ], + [ + "335m", + "671\u202fMB" + ], + [ + "335m-en-v1.5-fp16", + "671\u202fMB" + ] + ], + "image": false, + "author": "BGE Large Team" }, "deepseek-v2.5": { "url": "https://ollama.com/library/deepseek-v2.5", @@ -23633,27 +23893,7 @@ ] ], "image": false, - "author": "Deepseek AI" - }, - "paraphrase-multilingual": { - "url": "https://ollama.com/library/paraphrase-multilingual", - "description": "Sentence-transformers model that can be used for tasks like clustering or semantic search.", - "tags": [ - [ - "latest", - "563\u202fMB" - ], - [ - "278m", - "563\u202fMB" - ], - [ - "278m-mpnet-base-v2-fp16", - "563\u202fMB" - ] - ], - "image": false, - "author": "Paraphrase Team" + "author": "DeepSeek Team" }, "bespoke-minicheck": { "url": "https://ollama.com/library/bespoke-minicheck", @@ -23730,5 +23970,25 @@ ], "image": false, "author": "Bespoke Labs" + }, + "paraphrase-multilingual": { + "url": "https://ollama.com/library/paraphrase-multilingual", + "description": "Sentence-transformers model that can be used for tasks like clustering or semantic search.", + "tags": [ + [ + "latest", + "563\u202fMB" + ], + [ + "278m", + "563\u202fMB" + ], + [ + "278m-mpnet-base-v2-fp16", + "563\u202fMB" + ] + ], + "image": false, + "author": "Paraphrase Team" } } \ No newline at end of file diff --git a/src/available_models_descriptions.py b/src/available_models_descriptions.py index b9b3f8b..8a97d1a 100644 --- a/src/available_models_descriptions.py +++ b/src/available_models_descriptions.py @@ -1,4 +1,5 @@ descriptions = { + 'llama3.2': _("Meta's Llama 3.2 goes small with 1B and 3B models."), 'llama3.1': _("Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes."), 'gemma2': _("Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B."), 'qwen2.5': _("Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support."), @@ -21,87 +22,88 @@ 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."), 'nomic-embed-text': _("A high-performing open embedding model with a large token context window."), + 'mxbai-embed-large': _("State-of-the-art large embedding model from mixedbread.ai"), '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."), 'phi': _("Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities."), - '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."), - 'mxbai-embed-large': _("State-of-the-art large embedding model from mixedbread.ai"), 'starcoder2': _("StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters."), + 'llama2-uncensored': _("Uncensored Llama 2 model by George Sung and Jarrad Hope."), 'dolphin-mistral': _("The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8."), '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."), '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."), 'orca-mini': _("A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware."), - 'yi': _("Yi 1.5 is a high-performing, bilingual language model."), 'llava-llama3': _("A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks."), + 'qwen2.5-coder': _("The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing."), 'mistral-openorca': _("Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset."), 'starcoder': _("StarCoder is a code generation model trained on 80+ programming languages."), 'tinyllama': _("The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens."), - 'vicuna': _("General use chat model based on Llama and Llama 2 with 2K to 16K context sizes."), 'codestral': _("Codestral is Mistral AI’s first-ever code model designed for code generation tasks."), + 'vicuna': _("General use chat model based on Llama and Llama 2 with 2K to 16K context sizes."), 'llama2-chinese': _("Llama 2 based model fine tuned to improve Chinese dialogue ability."), + 'snowflake-arctic-embed': _("A suite of text embedding models by Snowflake, optimized for performance."), 'wizard-vicuna-uncensored': _("Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford."), + 'granite-code': _("A family of open foundation models by IBM for Code Intelligence"), 'codegeex4': _("A versatile model for AI software development scenarios, including code completion."), 'nous-hermes2': _("The powerful family of models by Nous Research that excels at scientific discussion and coding tasks."), - 'granite-code': _("A family of open foundation models by IBM for Code Intelligence"), + 'all-minilm': _("Embedding models on very large sentence level datasets."), '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."), 'aya': _("Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages."), - 'wizardlm2': _("State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases."), 'codeqwen': _("CodeQwen1.5 is a large language model pretrained on a large amount of code data."), + 'wizardlm2': _("State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases."), 'tinydolphin': _("An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama."), - 'all-minilm': _("Embedding models on very large sentence level 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."), 'openhermes': _("OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets."), + 'qwen2-math': _("Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o)."), 'bakllava': _("BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture."), '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."), - 'qwen2-math': _("Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o)."), - 'wizard-math': _("Model focused on math and logic problems"), 'llama3-gradient': _("This model extends LLama-3 8B's context length from 8k to over 1m tokens."), - 'neural-chat': _("A fine-tuned model based on Mistral with good coverage of domain and language."), 'deepseek-llm': _("An advanced language model crafted with 2 trillion bilingual tokens."), + 'wizard-math': _("Model focused on math and logic problems"), + 'glm4': _("A strong multi-lingual general language model with competitive performance to Llama 3."), + 'neural-chat': _("A fine-tuned model based on Mistral with good coverage of domain and language."), + 'reflection': _("A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course."), + 'llama3-chatqa': _("A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG)."), + 'mistral-large': _("Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages."), + 'moondream': _("moondream2 is a small vision language model designed to run efficiently on edge devices."), + 'xwinlm': _("Conversational model based on Llama 2 that performs competitively on various benchmarks."), 'phind-codellama': _("Code generation model based on Code Llama."), 'nous-hermes': _("General use models based on Llama and Llama 2 from Nous Research."), - 'xwinlm': _("Conversational model based on Llama 2 that performs competitively on various benchmarks."), 'sqlcoder': _("SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks"), 'dolphincoder': _("A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2."), - 'llama3-chatqa': _("A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG)."), 'yarn-llama2': _("An extension of Llama 2 that supports a context of up to 128k tokens."), - 'mistral-large': _("Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages."), - 'wizardlm': _("General use model based on Llama 2."), 'smollm': _("🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset."), + 'wizardlm': _("General use model based on Llama 2."), + 'deepseek-v2': _("A strong, economical, and efficient Mixture-of-Experts language model."), 'starling-lm': _("Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness."), - 'reflection': _("A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course."), - 'moondream': _("moondream2 is a small vision language model designed to run efficiently on edge devices."), - 'snowflake-arctic-embed': _("A suite of text embedding models by Snowflake, optimized for performance."), 'samantha-mistral': _("A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral."), 'solar': _("A compact, yet powerful 10.7B large language model designed for single-turn conversation."), '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."), - 'deepseek-v2': _("A strong, economical, and efficient Mixture-of-Experts language model."), 'stable-beluga': _("Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy."), - 'glm4': _("A strong multi-lingual general language model with competitive performance to Llama 3."), 'dolphin-phi': _("2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research."), 'wizardlm-uncensored': _("Uncensored version of Wizard LM model"), - 'llava-phi3': _("A new small LLaVA model fine-tuned from Phi 3 Mini."), 'hermes3': _("Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research"), + 'yi-coder': _("Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters."), + 'llava-phi3': _("A new small LLaVA model fine-tuned from Phi 3 Mini."), + 'internlm2': _("InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability."), 'yarn-mistral': _("An extension of Mistral to support context windows of 64K or 128K."), 'llama-pro': _("An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics."), 'medllama2': _("Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset."), - 'yi-coder': _("Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters."), - 'internlm2': _("InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability."), 'meditron': _("Open-source medical large language model adapted from Llama 2 to the medical domain."), 'nexusraven': _("Nexus Raven is a 13B instruction tuned model for function calling tasks."), 'nous-hermes2-mixtral': _("The Nous Hermes 2 model from Nous Research, now trained over Mixtral."), 'codeup': _("Great code generation model based on Llama2."), - 'everythinglm': _("Uncensored Llama2 based model with support for a 16K context window."), '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."), + 'everythinglm': _("Uncensored Llama2 based model with support for a 16K context window."), '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."), + 'wizard-vicuna': _("Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj."), 'mistrallite': _("MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts."), 'falcon2': _("Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens."), - 'wizard-vicuna': _("Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj."), 'duckdb-nsql': _("7B parameter text-to-SQL model made by MotherDuck and Numbers Station."), - 'qwen2.5-coder': _("The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing."), + 'minicpm-v': _("A series of multimodal LLMs (MLLMs) designed for vision-language understanding."), 'megadolphin': _("MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself."), 'notux': _("A top-performing mixture of experts model, fine-tuned with high-quality data."), 'goliath': _("A language model created by combining two fine-tuned Llama 2 70B models into one."), @@ -110,14 +112,13 @@ descriptions = { 'bge-m3': _("BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity."), 'mathstral': _("MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI."), 'dbrx': _("DBRX is an open, general-purpose LLM created by Databricks."), - 'minicpm-v': _("A series of multimodal LLMs (MLLMs) designed for vision-language understanding."), + 'solar-pro': _("Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU"), 'nuextract': _("A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3."), 'alfred': _("A robust conversational model designed to be used for both chat and instruct use cases."), 'firefunction-v2': _("An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities."), - 'solar-pro': _("Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU"), - 'bge-large': _("Embedding model from BAAI mapping texts to vectors."), 'reader-lm': _("A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks."), + 'bge-large': _("Embedding model from BAAI mapping texts to vectors."), 'deepseek-v2.5': _("An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct."), - 'paraphrase-multilingual': _("Sentence-transformers model that can be used for tasks like clustering or semantic search."), 'bespoke-minicheck': _("A state-of-the-art fact-checking model developed by Bespoke Labs."), + 'paraphrase-multilingual': _("Sentence-transformers model that can be used for tasks like clustering or semantic search."), } \ No newline at end of file