A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
14.8K Pulls 1 Tag Updated 2 months ago
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
1.2M Pulls 5 Tags Updated 7 months ago
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.
569.1K Pulls 5 Tags Updated 10 months ago
The 7B model released by Mistral AI, updated to version 0.3.
24.8M Pulls 84 Tags Updated 6 months ago
A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
3.3M Pulls 17 Tags Updated 6 months ago
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
2.3M Pulls 21 Tags Updated 1 year ago
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.
477.3K Pulls 32 Tags Updated 1 year ago
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
309.9K Pulls 17 Tags Updated 2 years ago
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
166.3K Pulls 17 Tags Updated 2 years ago
A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.
1.8M Pulls 70 Tags Updated 1 year ago
Codestral is Mistral AI’s first-ever code model designed for code generation tasks.
761K Pulls 17 Tags Updated 1 year ago
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
654.6K Pulls 120 Tags Updated 1 year ago
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
475.6K Pulls 17 Tags Updated 2 years ago
Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
490.1K Pulls 40 Tags Updated 1 year ago
OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.
385.4K Pulls 35 Tags Updated 2 years ago
A fine-tuned model based on Mistral with good coverage of domain and language.
351.7K Pulls 50 Tags Updated 2 years ago
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
310.4K Pulls 49 Tags Updated 2 years ago
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
179.9K Pulls 17 Tags Updated 1 year ago
An extension of Mistral to support context windows of 64K or 128K.
250.2K Pulls 33 Tags Updated 2 years ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
359.3K Pulls 16 Tags Updated 1 month ago