Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

4.9M  Pulls 95 Tags Updated  7 weeks ago

A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

167K  Pulls 17 Tags Updated  7 weeks 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.

54.1K  Pulls 17 Tags Updated  7 weeks ago

Qwen2 is a new series of large language models from Alibaba group

3M  Pulls 97 Tags Updated  3 months ago

The 7B model released by Mistral AI, updated to version 0.3.

3.4M  Pulls 84 Tags Updated  3 months ago

A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.

404.7K  Pulls 69 Tags Updated  4 months ago

Command R is a Large Language Model optimized for conversational interaction and long context tasks.

192.5K  Pulls 32 Tags Updated  12 days ago

Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.

94.1K  Pulls 21 Tags Updated  12 days ago

Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research

30.6K  Pulls 49 Tags Updated  2 weeks ago

A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.

21.9K  Pulls 33 Tags Updated  8 weeks ago

18.2K  Pulls 1 Tag Updated  6 weeks ago

An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.

8,587  Pulls 17 Tags Updated  8 weeks ago

uncensored version of llama3.1:8B

3,242  Pulls 1 Tag Updated  5 weeks ago

Ablitered v3 llama-3.1 8b with uncensored prompt

2,727  Pulls 38 Tags Updated  5 weeks ago

This is an uncensored version of Llama 3.1 8B Instruct with an uncensored prompt.

1,728  Pulls 45 Tags Updated  5 weeks ago

Llama-3.1-Storm-8B outperforms both Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B! 🤗 Blog: https://huggingface.co/blog/akjindal53244/llama31-storm8b

1,658  Pulls 3 Tags Updated  3 weeks ago

1,428  Pulls 1 Tag Updated  6 weeks ago

Qwen2 with tools enabled

1,161  Pulls 3 Tags Updated  3 weeks ago

Hermes 3 Series of Llama-3.1 Models by NousResearch

834  Pulls 16 Tags Updated  3 weeks ago

A function calling model from the xLAM model family.

746  Pulls 2 Tags Updated  6 weeks ago

713  Pulls 1 Tag Updated  7 weeks ago

385  Pulls 1 Tag Updated  7 weeks ago

368  Pulls 5 Tags Updated  3 weeks ago

AGI-0 Labs' Reflection Model : A model created by agi0labs based on mattshumer/Reflection-Llama-3.1-70B, offering similar results in language understanding and generation tasks.

361  Pulls 1 Tag Updated  4 days ago

Outperforms Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B

313  Pulls 6 Tags Updated  3 weeks ago