Commit
•
528b02e
1
Parent(s):
41c636f
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
---
|
| 4 |
-
This is an fp16 copy of [jarradh/llama2_70b_chat_uncensored](https://huggingface.co/jarradh/llama2_70b_chat_uncensored) for faster downloading and less disk space usage than the fp32 original. I simply imported the model to CPU with torch_dtype=torch.float16 and then exported it again.
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
---
|
| 4 |
+
This is an fp16 copy of [jarradh/llama2_70b_chat_uncensored](https://huggingface.co/jarradh/llama2_70b_chat_uncensored) for faster downloading and less disk space usage than the fp32 original. I simply imported the model to CPU with torch_dtype=torch.float16 and then exported it again.
|
| 5 |
+
|
| 6 |
+
Arguable a better name for this model would be Wizard-Vicuna-Uncensored-Llama-2-70B-fp16, but to avoid confusion I'm sticking with jarradh's naming scheme.
|