Commit
•
715268e
1
Parent(s):
00836b3
ajustes
Browse files
README.md
CHANGED
|
@@ -9,6 +9,8 @@ library_name: transformers
|
|
| 9 |
|
| 10 |
# Quantization 4Bits - 4.92 GB GPU memory usage for inference:
|
| 11 |
|
|
|
|
|
|
|
| 12 |
```
|
| 13 |
$ nvidia-smi
|
| 14 |
+-----------------------------------------------------------------------------+
|
|
|
|
| 9 |
|
| 10 |
# Quantization 4Bits - 4.92 GB GPU memory usage for inference:
|
| 11 |
|
| 12 |
+
** Vide same fine-tuning for Llama2-7B-Chat: [https://huggingface.co/nlpulse/llama2-7b-chat-english_quotes](https://huggingface.co/nlpulse/llama2-7b-chat-english_quotes)
|
| 13 |
+
|
| 14 |
```
|
| 15 |
$ nvidia-smi
|
| 16 |
+-----------------------------------------------------------------------------+
|