Commit
•
3115b27
1
Parent(s):
da0e898
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,12 @@ inference: false
|
|
| 7 |
|
| 8 |
# LLaVA GPTQ Model Card
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
These files are GPTQ model files for [LLaVA-LLaMA-2-13B-Chat-Preview](https://huggingface.co/liuhaotian/llava-llama-2-13b-chat-lightning-preview).
|
| 11 |
|
| 12 |
## Model details
|
|
|
|
| 7 |
|
| 8 |
# LLaVA GPTQ Model Card
|
| 9 |
|
| 10 |
+
**NOTE: To use the GPTQ quantized LLaVA checkpoints, you need to use `text-generation-webui`, and the support for LLaMA-2 is WIP. We are working on the PR.**
|
| 11 |
+
|
| 12 |
+
You can try it out [here](https://github.com/haotian-liu/text-generation-webui).
|
| 13 |
+
Instructions and detailed stories here: https://github.com/haotian-liu/LLaVA/issues/310#issuecomment-1657552223
|
| 14 |
+
PR: https://github.com/oobabooga/text-generation-webui/pull/3377
|
| 15 |
+
|
| 16 |
These files are GPTQ model files for [LLaVA-LLaMA-2-13B-Chat-Preview](https://huggingface.co/liuhaotian/llava-llama-2-13b-chat-lightning-preview).
|
| 17 |
|
| 18 |
## Model details
|