Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
|
|
|
| 1 |
+
4-bit quant of llama part of llava https://github.com/haotian-liu/LLaVA https://huggingface.co/liuhaotian/LLaVA-13b-delta-v0
|
| 2 |
+
|
| 3 |
+
quantized by:
|
| 4 |
+
```
|
| 5 |
+
CUDA_VISIBLE_DEVICES=0 python llama.py /workspace/LLaVA-13B-v0/ c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors llava-13b-v0-4bit-128g.safetensors
|
| 6 |
+
```
|
| 7 |
+
|
| 8 |
+
on https://github.com/oobabooga/GPTQ-for-LLaMa CUDA branch of GPTQ (commit `57a2629`)
|
| 9 |
+
|
| 10 |
+
see: https://github.com/oobabooga/text-generation-webui/issues/1355#issuecomment-1518116906
|
| 11 |
+
|
| 12 |
---
|
| 13 |
license: other
|
| 14 |
---
|