Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,10 @@ A lightly post-trained version of [talkie-lm/talkie-1930-13b-base](https://huggi
|
|
| 12 |
|
| 13 |
Recommended sampling settings are `temp=0.5, min_p=0.05, top_k=40, repetition_penalty=1.2, repetition_context_size=128`. Like the base model, it has a max context size of 2048. It additionally retians the (limited) few shot learning ability of the base model - going from 7.73% GSM8K at 1-shot to 11.30% at 2-shot to 12.36% at 4-shot.
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Chat template
|
| 16 |
|
| 17 |
This model uses a standard `user` / `assistant` chat API surface, but renders
|
|
|
|
| 12 |
|
| 13 |
Recommended sampling settings are `temp=0.5, min_p=0.05, top_k=40, repetition_penalty=1.2, repetition_context_size=128`. Like the base model, it has a max context size of 2048. It additionally retians the (limited) few shot learning ability of the base model - going from 7.73% GSM8K at 1-shot to 11.30% at 2-shot to 12.36% at 4-shot.
|
| 14 |
|
| 15 |
+
|
| 16 |
+
## Safety Disclaimer
|
| 17 |
+
|
| 18 |
+
This model is ancient and safety training is minimal. It may generate objectionable content, hateful content, or flat-up wrong content. Thus it is strictly for experimental purposes and I strongly recommend against its use in any user-facing application.
|
| 19 |
## Chat template
|
| 20 |
|
| 21 |
This model uses a standard `user` / `assistant` chat API surface, but renders
|