ilotoki_thu/alpaca_lora_4bit
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
John Smith
2023-04-22 16:09:38 +08:00
committed by GitHub
parent 33a76b00ca
commit 51bf103269
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -43,6 +43,12 @@ It's fast on a 3070 Ti mobile. Uses 5-6 GB of GPU RAM.
* Removed bitsandbytes from requirements * Removed bitsandbytes from requirements
* Added pip installable branch based on winglian's PR * Added pip installable branch based on winglian's PR
* Added cuda backend quant attention and fused mlp from GPTQ_For_Llama. * Added cuda backend quant attention and fused mlp from GPTQ_For_Llama.
* Added lora patch for GPTQ_For_Llama triton backend.
```
from monkeypatch.gptq_for_llala_lora_monkey_patch import inject_lora_layers
inject_lora_layers(model, lora_path, device, dtype)
```
# Requirements # Requirements
gptq-for-llama <br> gptq-for-llama <br>