🌋 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.
4.8M Pulls 98 Tags Updated 14 months ago
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
630.8K Pulls 4 Tags Updated 11 months ago
A new small LLaVA model fine-tuned from Phi 3 Mini.
86K Pulls 4 Tags Updated 11 months ago
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
89.7M Pulls 93 Tags Updated 4 months ago
Meta Llama 3: The most capable openly available LLM to date
7.8M Pulls 68 Tags Updated 10 months ago
Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.
309.8K Pulls 53 Tags Updated 11 months ago
Conversational model based on Llama 2 that performs competitively on various benchmarks.
85.4K Pulls 80 Tags Updated 17 months ago
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
113.3K Pulls 17 Tags Updated 16 months ago
A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
101.1K Pulls 35 Tags Updated 11 months ago
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
60.5K Pulls 33 Tags Updated 8 months ago
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
555.2K Pulls 49 Tags Updated 5 months ago
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
1.8M Pulls 9 Tags Updated 5 months ago
Llama 2 based model fine tuned to improve Chinese dialogue ability.
151.7K Pulls 35 Tags Updated 17 months ago
An advanced language model crafted with 2 trillion bilingual tokens.
140.1K Pulls 64 Tags Updated 16 months ago
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
72.1K Pulls 38 Tags Updated 17 months ago
DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
19.7K Pulls 9 Tags Updated 4 days ago
5 Pulls 1 Tag Updated 3 months ago
Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
10.8K Pulls 13 Tags Updated 4 months ago
A lightweight vision model
4,992 Pulls 1 Tag Updated 11 months ago
Pixie is a combined model powered by dolphin-llama3 and llava who can break complex problems into smaller pieces and find the best solutions using her own pattern. Not only text based, she can read images as well.
3,148 Pulls 1 Tag Updated 11 months ago