Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,8 @@ Tool used:
|
|
13 |
|
14 |
- qwopqwop200/GPTQ-for-LLaMa
|
15 |
|
|
|
|
|
16 |
Note: QLoRA training os environ Windows, Python 3.11, CUDA 11.8 on 24GB VRAM:
|
17 |
|
18 |
Know issue: load 4bit version in oobabooga/text-generation-webui give gibberish prompt, use ExLlama instead of AutoGPTQ
|
|
|
13 |
|
14 |
- qwopqwop200/GPTQ-for-LLaMa
|
15 |
|
16 |
+
- ggerganov/llama.cpp
|
17 |
+
|
18 |
Note: QLoRA training os environ Windows, Python 3.11, CUDA 11.8 on 24GB VRAM:
|
19 |
|
20 |
Know issue: load 4bit version in oobabooga/text-generation-webui give gibberish prompt, use ExLlama instead of AutoGPTQ
|