Downloads · 30 days
177
15% of all-time downloads
llava-7b-v0-4bit-128g
wojtab/llava-7b-v0-4bit-128g
llava-7b-v0-4bit-128g is a text generation model from wojtab. Use it when you need the model to write or continue text. It is set up for transformers.
4-bit quant of llama part of llava https://github.com/haotian-liu/LLaVA https://huggingface.co/liuhaotian/LLaVA-7b-delta-v0
All-time downloads
1.2K
Public
Repo size
4 GB
Likes
11
Public
Repo makeup
Click a slice to open those files.
.safetensors4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- May 1, 2023
- Updated
- May 5, 2023
- SHA
- f3649fac
Try a prompt
Model card
From the Hugging Face model README
4-bit quant of llama part of llava https://github.com/haotian-liu/LLaVA https://huggingface.co/liuhaotian/LLaVA-7b-delta-v0
quantized by:
CUDA_VISIBLE_DEVICES=0 python llama.py /workspace/LLaVA-7B-v0/ c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors llava-7b-v0-4bit-128g.safetensors
on https://github.com/oobabooga/GPTQ-for-LLaMa CUDA branch of GPTQ (commit 57a2629)
NOT COMPATIBILE WITH TEXT-GENERATION-WEBUI YET
(multimodality isn't, text inference is) waiting for this PR: https://github.com/oobabooga/text-generation-webui/pull/1741
license: other
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- May 1, 2023
- Updated
- May 5, 2023