Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.

42.8K  Pulls 49 Tags Updated  10 months ago

A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.

42.7K  Pulls 17 Tags Updated  3 weeks ago

A strong, economical, and efficient Mixture-of-Experts language model.

41.9K  Pulls 34 Tags Updated  10 days ago

A strong multi-lingual general language model with competitive performance to Llama 3.

41.3K  Pulls 32 Tags Updated  2 months ago

2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.

41.1K  Pulls 15 Tags Updated  8 months ago

39.7K  Pulls 1 Tag Updated  5 months ago

BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.

38.5K  Pulls 17 Tags Updated  9 months ago

A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

36.7K  Pulls 17 Tags Updated  5 days ago

Uncensored version of Wizard LM model

36K  Pulls 18 Tags Updated  12 months ago

MiniCPM-V surpasses proprietary models such as GPT-4V, Gemini Pro, Qwen-VL and Claude 3 in overall performance, and support multimodal conversation for over 30 languages.

34K  Pulls 8 Tags Updated  3 months ago

An extension of Mistral to support context windows of 64K or 128K.

33.8K  Pulls 33 Tags Updated  8 months ago

A new small LLaVA model fine-tuned from Phi 3 Mini.

33.6K  Pulls 4 Tags Updated  4 months ago

An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

33K  Pulls 33 Tags Updated  8 months ago

Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.

32.7K  Pulls 17 Tags Updated  11 months ago

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

31.5K  Pulls 49 Tags Updated  2 weeks ago

Open-source medical large language model adapted from Llama 2 to the medical domain.

30.7K  Pulls 22 Tags Updated  9 months ago

Nexus Raven is a 13B instruction tuned model for function calling tasks.

30.1K  Pulls 32 Tags Updated  9 months ago

The Nous Hermes 2 model from Nous Research, now trained over Mixtral.

29.8K  Pulls 18 Tags Updated  8 months ago

InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.

28.7K  Pulls 65 Tags Updated  2 months ago

Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

28.1K  Pulls 67 Tags Updated  9 days ago

Great code generation model based on Llama2.

27.9K  Pulls 19 Tags Updated  10 months ago

Uncensored Llama2 based model with support for a 16K context window.

26.2K  Pulls 18 Tags Updated  8 months ago

MiniCPM-V 2.6 is the latest and most capable model in the MiniCPM-V series. It exhibits a significant performance improvement over MiniCPM-Llama3-V 2.5

26.2K  Pulls 1 Tag Updated  4 weeks ago

Kevin is an advanced AI-powered app designed to offer a personalized conversational experience. By leveraging state-of-the-art technologies in natural language processing, machine learning, and speech recognition, Kevin aims to understand and learn

25.9K  Pulls 1 Tag Updated  4 months ago

🎩 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.

23.6K  Pulls 18 Tags Updated  9 months ago