Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind.
108.4K Pulls 69 Tags Updated 10 days ago
Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
562.8K Pulls 102 Tags Updated 3 weeks ago
The 7B model released by Mistral AI, updated to version 0.2.
275.0K Pulls 53 Tags Updated 2 months ago
A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI.
82.6K Pulls 34 Tags Updated 4 weeks ago
🌋 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.
62.4K Pulls 98 Tags Updated 4 weeks ago
A fine-tuned model based on Mistral with good coverage of domain and language.
13.8K Pulls 50 Tags Updated 2 months ago
A large language model that can use text prompts to generate and discuss code.
197.9K Pulls 199 Tags Updated 4 weeks ago
An uncensored, fine-tuned model based on the Mixtral mixture of experts model that excels at coding tasks. Created by Eric Hartford.
131.9K Pulls 70 Tags Updated 2 months ago
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
100.4K Pulls 17 Tags Updated 4 months ago
Uncensored Llama 2 model by George Sung and Jarrad Hope.
80.3K Pulls 34 Tags Updated 4 months ago
Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.
54.3K Pulls 18 Tags Updated 4 weeks ago
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
52.1K Pulls 119 Tags Updated 4 months ago
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
48.7K Pulls 102 Tags Updated 2 months ago
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.6.
43.4K Pulls 103 Tags Updated 7 weeks ago
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
30.4K Pulls 49 Tags Updated 4 months ago
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
29.9K Pulls 111 Tags Updated 4 months ago
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 72B parameters
25.1K Pulls 319 Tags Updated 3 weeks ago
Zephyr beta is a fine-tuned 7B version of mistral that was trained on on a mix of publicly available, synthetic datasets.
22.4K Pulls 34 Tags Updated 2 months ago
OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.
21.7K Pulls 35 Tags Updated 2 months ago
Llama 2 based model fine tuned to improve Chinese dialogue ability.
19.0K Pulls 35 Tags Updated 4 months ago
State-of-the-art code generation model
18.7K Pulls 67 Tags Updated 8 weeks ago
The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
17.5K Pulls 36 Tags Updated 2 months ago
Code generation model based on Code Llama.
16.4K Pulls 49 Tags Updated 2 months ago
A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.
16.3K Pulls 50 Tags Updated 7 weeks ago
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.
13.6K Pulls 33 Tags Updated 3 months ago