-
dolphin-phi
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
3B40.1K Pulls 15 Tags Updated 8 months ago
-
deepseek-v2
A strong, economical, and efficient Mixture-of-Experts language model.
39.9K Pulls 34 Tags Updated 4 days ago
-
glm4
A strong multi-lingual general language model with competitive performance to Llama 3.
9B38.5K Pulls 32 Tags Updated 2 months ago
-
phi3.5
A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.
3B37.4K Pulls 17 Tags Updated 2 weeks ago
-
bakllava
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
Vision 7B37.4K Pulls 17 Tags Updated 8 months ago
-
wizardlm-uncensored
Uncensored version of Wizard LM model
13B35.1K Pulls 18 Tags Updated 12 months ago
-
hhao/openbmb-minicpm-llama3-v-2_5
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.
Vision33.5K Pulls 8 Tags Updated 3 months ago
-
yarn-mistral
An extension of Mistral to support context windows of 64K or 128K.
7B32.9K Pulls 33 Tags Updated 8 months ago
-
medllama2
Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.
7B32K Pulls 17 Tags Updated 10 months ago
-
llama-pro
An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
8B31.9K Pulls 33 Tags Updated 8 months ago
-
llava-phi3
A new small LLaVA model fine-tuned from Phi 3 Mini.
Vision 3B30.8K Pulls 4 Tags Updated 4 months ago
-
meditron
Open-source medical large language model adapted from Llama 2 to the medical domain.
7B 70B29.8K Pulls 22 Tags Updated 9 months ago
-
nous-hermes2-mixtral
The Nous Hermes 2 model from Nous Research, now trained over Mixtral.
8x7B29.2K Pulls 18 Tags Updated 7 months ago
-
nexusraven
Nexus Raven is a 13B instruction tuned model for function calling tasks.
13B29.1K Pulls 32 Tags Updated 9 months ago
-
hermes3
Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research
Tools 8B 70B28K Pulls 49 Tags Updated 12 days ago
-
codeup
Great code generation model based on Llama2.
Code 13B27.2K Pulls 19 Tags Updated 10 months ago
-
tyllama/kevin
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
8B25.9K Pulls 1 Tag Updated 4 months ago
-
aiden_lu/minicpm-v2.6
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
Vision 7B25.7K Pulls 1 Tag Updated 3 weeks ago
-
everythinglm
Uncensored Llama2 based model with support for a 16K context window.
13B25.6K Pulls 18 Tags Updated 8 months ago
-
internlm2
InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.
7B25.4K Pulls 65 Tags Updated 2 months ago
-
hellord/mxbai-embed-large-v1
Embedding23.6K Pulls 1 Tag Updated 5 months ago
-
magicoder
🎩 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.
Code 7B23K Pulls 18 Tags Updated 9 months ago
-
stablelm-zephyr
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
22.6K Pulls 17 Tags Updated 9 months ago
-
codebooga
A high-performing code instruct model created by merging two existing code models.
Code 34B22K Pulls 16 Tags Updated 10 months ago
-
yi-coder
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.
Code 9B21.6K Pulls 67 Tags Updated 3 days ago