Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,9 @@ tags:
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# llama-30b-int4
|
| 9 |
-
This LoRA trained for 3 epochs and has been converted to int4 (4bit) via GPTQ method.
|
|
|
|
|
|
|
| 10 |
|
| 11 |
https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
| 12 |
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# llama-30b-int4
|
| 9 |
+
This LoRA trained for 3 epochs and has been converted to int4 (4bit) via GPTQ method.
|
| 10 |
+
|
| 11 |
+
Use the one of the two **safetensors** versions, the **pt** version is an old quantization that is no longer supported and will be removed in the future. Make sure you only have **ONE** checkpoint from the two in your model directory! See the repo below for more info.
|
| 12 |
|
| 13 |
https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
| 14 |
|