mapler / llava-mistral

A new LLaVA model fine-tuned from Mistral's 7B model

457 Pulls Updated 3 months ago

3 months ago

92bbf2ed9e9a · 5.0GB

model
llama
·
7.24B
·
Q5_K_S
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user {{ .Prompt }}<|im_end|> {{ end }}<|im_start|>assistant {{ .Response }}<|im_end|>

Readme

Model details

Model type:
LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data.
It is an auto-regressive language model, based on the transformer architecture.
Base LLM: mistralai/Mistral-7B-Instruct-v0.2

Model date:
LLaVA-v1.6-Mistral-7B was trained in December 2023.

Paper or resources for more information:
https://llava-vl.github.io/

License

mistralai/Mistral-7B-Instruct-v0.2 license.

Where to send questions or comments about the model:
https://github.com/haotian-liu/LLaVA/issues

Intended use

Primary intended uses:
The primary use of LLaVA is research on large multimodal models and chatbots.

Primary intended users:
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

  • 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
  • 158K GPT-generated multimodal instruction-following data.
  • 500K academic-task-oriented VQA data mixture.
  • 50K GPT-4V data mixture.
  • 40K ShareGPT data.

Evaluation dataset

A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.