'mistral-nemo':_("A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA."),
'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."),
'qwen2':_("Qwen2 is a new series of large language models from Alibaba group"),
'deepseek-coder-v2':_("An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks."),
'phi3':_("Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft."),
'mistral':_("The 7B model released by Mistral AI, updated to version 0.3."),
'mixtral':_("A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes."),
'codegemma':_("CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following."),
'command-r':_("Command R is a Large Language Model optimized for conversational interaction and long context tasks."),
'command-r-plus':_("Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases."),
'llava':_("🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6."),
'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."),
'orca-mini':_("A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware."),
'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."),
'yi':_("Yi 1.5 is a high-performing, bilingual language model."),
'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."),
'wizardlm2':_("State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases."),
'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."),
'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."),
'llama3-chatqa':_("A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG)."),
'wizardlm':_("General use model based on Llama 2."),
'starling-lm':_("Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness."),
'codegeex4':_("A versatile model for AI software development scenarios, including code completion."),
'snowflake-arctic-embed':_("A suite of text embedding models by Snowflake, optimized for performance."),
'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."),
'smollm':_("🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset."),
'stable-beluga':_("🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset."),
'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)."),
'dolphin-phi':_("2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research."),
'deepseek-v2':_("A strong, economical, and efficient Mixture-of-Experts language model."),
'llama-pro':_("An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics."),
'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."),
'mistrallite':_("MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts."),
'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."),
'falcon2':_("Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens."),
