|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
# Experimental GGUF Quantized LLaVA 1.6 34B |
|
|
|
Seem to work decently well. Unknown limitations compared to original model |
|
|
|
Notes: Was prepared with a unofficial script, and is likely missing some data and lacking some performance. Will update quants when better script is available |
|
|
|
## Provided files |
|
| Name | Quant method | Bits | Size | Use case | |
|
| ---- | ---- | ---- | ---- | ----- | |
|
| [llava-v1.6-34b.Q3_K_XS.gguf](https://huggingface.co/cjpais/llava-v1.6-34B-gguf/blob/main/llava-1.6-34b.Q3_K_XS.gguf) | Q3_K_XS | 3 | 14.2 GB| very small, high quality loss | |
|
| [llava-v1.6-34b.Q3_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-34B-gguf/blob/main/llava-1.6-34b.Q3_K.gguf) | Q3_K_M | 3 | 16.7 GB| very small, high quality loss | |
|
| [llava-v1.6-34b.Q4_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-34B-gguf/blob/main/llava-1.6-34b.Q4_K_M.gguf) | Q4_K_M | 4 | 20.66 GB| medium, balanced quality - recommended | |
|
| [llava-v1.6-34b.Q5_K_S.gguf](https://huggingface.co/cjpais/llava-v1.6-34B-gguf/blob/main/llava-1.6-34b.Q5_K_S.gguf) | Q5_K_S | 5 | 23.7 GB| large, low quality loss - recommended | |
|
| [llava-v1.6-34b.Q5_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-34B-gguf/blob/main/ggml-model-Q5_K.gguf) | Q5_K_M | 5 | 24.3 GB| large, very low quality loss - recommended | |
|
|
|
<br> |
|
<br> |
|
|
|
# ORIGINAL LLaVA Model Card |
|
|
|
## 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: [NousResearch/Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B) |
|
|
|
**Model date:** |
|
LLaVA-v1.6-34B was trained in December 2023. |
|
|
|
**Paper or resources for more information:** |
|
https://llava-vl.github.io/ |
|
|
|
## License |
|
[NousResearch/Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B) 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. |
|
|
