Commit
·
0c2b8a0
1
Parent(s):
ef37c45
oops
Browse files
README.md
CHANGED
|
@@ -22,6 +22,7 @@ I have since restarted training with the new format B from the tool and it seems
|
|
| 22 |
|
| 23 |
# How to test?
|
| 24 |
1. Download LLaMA-13B-HF: https://huggingface.co/Neko-Institute-of-Science/LLaMA-13B-HF
|
|
|
|
| 25 |
3. Load ooba: ```python server.py --listen --model LLaMA-13B-HF --load-in-8bit --chat --lora checkpoint-xxxx```
|
| 26 |
4. Instruct mode: Vicuna-v1
|
| 27 |
|
|
|
|
| 22 |
|
| 23 |
# How to test?
|
| 24 |
1. Download LLaMA-13B-HF: https://huggingface.co/Neko-Institute-of-Science/LLaMA-13B-HF
|
| 25 |
+
2. Download the checkpoint-xxxx you want into the loras folder.
|
| 26 |
3. Load ooba: ```python server.py --listen --model LLaMA-13B-HF --load-in-8bit --chat --lora checkpoint-xxxx```
|
| 27 |
4. Instruct mode: Vicuna-v1
|
| 28 |
|