| glm4-chat-1m | en, zh | GLM4 is the open source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. | 1048K |
| mistral-nemo-instruct | en, fr, de, es, it, pt, zh, ru, ja | The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-Nemo-Base-2407 | 1024K |
| internlm2.5-chat-1m | en, zh | InternLM2.5 series of the InternLM model supports 1M long-context | 262K |
| | | |
| c4ai-command-r-v01 | en, fr, de, es, it, pt, ja, ko, zh, ar | C4AI Command-R(+) is a research release of a 35 and 104 billion parameter highly performant generative model. | 131K |
| chatglm3-128k | en, zh | ChatGLM3 is the third generation of ChatGLM, still open-source and trained on Chinese and English data. | 131K |
| codegeex4 | en, zh | the open-source version of the latest CodeGeeX4 model series | 131K |
| glm4-chat | en, zh | GLM4 is the open source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. | 131K |
| llama-3.1-instruct | en, de, fr, it, pt, hi, es, th | The Llama 3.1 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. | 131K |
| mistral-large-instruct | en, fr, de, es, it, pt, zh, ru, ja, ko | Mistral-Large-Instruct-2407 is an advanced dense Large Language Model (LLM) of 123B parameters with state-of-the-art reasoning, knowledge and coding capabilities. | 131K |
| phi-3-mini-128k-instruct | en | The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. | 128K |
| code-llama-instruct | en | Code-Llama-Instruct is an instruct-tuned version of the Code-Llama LLM. | 100K |
| | | |
| mixtral-8x22B-instruct-v0.1 | en, fr, it, de, es | The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1, specializing in chatting. | 65K |
| codeqwen1.5-chat | en, zh | CodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. | 65K |
| csg-wukong-chat-v0.1 | en | csg-wukong-1B is a 1 billion-parameter small language model(SLM) pretrained on 1T tokens. | 32K |
| chatglm3-32k | en, zh | ChatGLM3 is the third generation of ChatGLM, still open-source and trained on Chinese and English data. | 32K |
| internlm2-chat | en, zh | The second generation of the InternLM model, InternLM2. | 32K |
| internlm2.5-chat | en, zh | InternLM2.5 series of the InternLM model. | 32K |
| internvl-chat | en, zh | InternVL 1.5 is an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. | 32K |
| internvl2 | en, zh | InternVL 2 is an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. | 32K |
| mistral-instruct-v0.3 | en | The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1. | 32K |
| mixtral-instruct-v0.1 | en, fr, it, de, es | Mistral-8x7B-Instruct is a fine-tuned version of the Mistral-8x7B LLM, specializing in chatting. | 32K |
| qwen-chat | en, zh | Qwen-chat is a fine-tuned version of the Qwen LLM trained with alignment techniques, specializing in chatting. | 32K |
| qwen1.5-chat | en, zh | Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. | 32K |
| qwen1.5-moe-chat | en, zh | Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data. | 32K |
| qwen2-instruct | en, zh | Qwen2 is the new series of Qwen large language models | 32K |
| qwen2-moe-instruct | en, zh | Qwen2 is the new series of Qwen large language models. | 32K |
| MiniCPM-V-2.6 | en, zh | MiniCPM-V 2.6 is the latest model in the MiniCPM-V series. The model is built on SigLip-400M and Qwen2-7B with a total of 8B parameters. | 32K |
| Yi-1.5-chat-16k | en, zh | Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. | 16K |
| aquila2-chat-16k | zh | AquilaChat2-16k series models are the long-text chat models | 16K |
| deepseek-coder-instruct | en, zh | deepseek-coder-instruct is a model initialized from deepseek-coder-base and fine-tuned on 2B tokens of instruction data. | 16K |
| chatglm3 | en, zh | ChatGLM3 is the third generation of ChatGLM, still open-source and trained on Chinese and English data. | 8K |
| codeshell-chat | en, zh | CodeShell is a multi-language code LLM developed by the Knowledge Computing Lab of Peking University. | 8K |
| cogvlm2 | en, zh | CogVLM2 have achieved good results in many lists compared to the previous generation of CogVLM open source models. Its excellent performance can compete with some non-open source models. | 8K |
| cogvlm2-video-llama3-chat | en, zh | CogVLM2-Video achieves state-of-the-art performance on multiple video question answering tasks. | 8K |
| gemma-2-it | en | Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. | 8K |
| gemma-it | en | Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. | 8K |
| glm-4v | en, zh | GLM4 is the open source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. | 8K |
| llama-3-instruct | en | The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. | 8K |
| MiniCPM-Llama3-V-2_5 | en, zh | MiniCPM-Llama3-V 2.5 is the latest model in the MiniCPM-V series. The model is built on SigLip-400M and Llama3-8B-Instruct with a total of 8B parameters. | 8K |
| mistral-instruct-v0.1 | en | Mistral-7B-Instruct is a fine-tuned version of the Mistral-7B LLM on public datasets, specializing in chatting. | 8K |
| mistral-instruct-v0.2 | en | The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1. | 8K |
| openhermes-2.5 | en | Openhermes 2.5 is a fine-tuned version of Mistral-7B-v0.1 on primarily GPT-4 generated data. | 8K |
| telechat | en, zh | The TeleChat is a large language model developed and trained by China Telecom Artificial Intelligence Technology Co., LTD. The 7B model base is trained with 1.5 trillion Tokens and 3 trillion Tokens and Chinese high-quality corpus. | 8K |
| zephyr-7b-alpha | en | Zephyr-7B-α is the first model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1. | 8K |
| zephyr-7b-beta | en | Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 | 8K |
| aquila2-chat | zh | Aquila2-chat series models are the chat models | 2K |
| OmniLMM | en, zh | OmniLMM is a family of open-source large multimodal models (LMMs) adept at vision & language modeling. | 2K |
| wizardmath-v1.0 | en | WizardMath is an open-source LLM trained by fine-tuning Llama2 with Evol-Instruct, specializing in math. | 2K |
| xverse-chat | en, zh | XVERSEB-Chat is the aligned version of model XVERSE. | 2K |
| baichuan-2-chat | en, zh | Baichuan2-chat is a fine-tuned version of the Baichuan LLM, specializing in chatting. | 4K |
| deepseek-chat | en, zh | DeepSeek LLM is an advanced language model comprising 67 billion parameters. It has been trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese. | 4K |
| deepseek-vl-chat | en, zh | DeepSeek-VL possesses general multimodal understanding capabilities, capable of processing logical diagrams, web pages, formula recognition, scientific literature, natural images, and embodied intelligence in complex scenarios. | 4K |
| gorilla-openfunctions-v1 | en | OpenFunctions is designed to extend Large Language Model (LLM) Chat Completion feature to formulate executable APIs call given natural language instructions and API context. | 4K |
| gorilla-openfunctions-v2 | en | OpenFunctions is designed to extend Large Language Model (LLM) Chat Completion feature to formulate executable APIs call given natural language instructions and API context. | 4K |
| llama-2-chat | en | Llama-2-Chat is a fine-tuned version of the Llama-2 LLM, specializing in chatting. | 4K |
| minicpm-2b-dpo-bf16 | zh | MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings. | 4K |
| minicpm-2b-dpo-fp16 | zh | MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings. | 4K |
| minicpm-2b-dpo-fp32 | zh | MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings. | 4K |
| minicpm-2b-sft-bf16 | zh | MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings. | 4K |
| minicpm-2b-sft-fp32 | zh | MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings. | 4K |
| orion-chat | en, zh | Orion-14B series models are open-source multilingual large language models trained from scratch by OrionStarAI. | 4K |
| orion-chat-rag | en, zh | Orion-14B series models are open-source multilingual large language models trained from scratch by OrionStarAI. | 4K |
| phi-3-mini-4k-instruct | en | The Phi-3-Mini-4k-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. | 4K |
| qwen-vl-chat | en, zh | Qwen-VL-Chat supports more flexible interaction, such as multiple image inputs, multi-round question answering, and creative capabilities. | 4K |
| Starling-LM | en, zh | We introduce Starling-7B, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). The model harnesses the power of our new GPT-4 labeled ranking dataset | 4K |
| Yi-1.5-chat | en, zh | Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. | 4K |
| Yi-chat | en, zh | The Yi series models are large language models trained from scratch by developers at 01.AI. | 4K |
| yi-vl-chat | en, zh | Yi Vision Language (Yi-VL) model is the open-source, multimodal version of the Yi Large Language Model (LLM) series, enabling content comprehension, recognition, and multi-round conversations about images. | 4K |
| wizardcoder-python-v1.0 | en | No description provided | 100K |