Update README.md
Browse files
README.md
CHANGED
@@ -37,7 +37,7 @@ inference:
|
|
37 |
|
38 |
# opt-peter-1pt3B-1E-ps_DS-msgs_Ep-2_Bs-4
|
39 |
|
40 |
-
This model is a fine-tuned version of [pszemraj/opt-peter-1.3B-1E](https://huggingface.co/pszemraj/opt-peter-1.3B-1E) on
|
41 |
It achieves the following results on the evaluation set:
|
42 |
- eval_loss: 3.4220
|
43 |
- eval_runtime: 954.9678
|
@@ -48,11 +48,13 @@ It achieves the following results on the evaluation set:
|
|
48 |
|
49 |
## Model description
|
50 |
|
51 |
-
|
|
|
52 |
|
53 |
## Intended uses & limitations
|
54 |
|
55 |
-
|
|
|
56 |
|
57 |
## Training and evaluation data
|
58 |
|
|
|
37 |
|
38 |
# opt-peter-1pt3B-1E-ps_DS-msgs_Ep-2_Bs-4
|
39 |
|
40 |
+
This model is a fine-tuned version of [pszemraj/opt-peter-1.3B-1E](https://huggingface.co/pszemraj/opt-peter-1.3B-1E) on 80k Whatsapp/iMessages (mine).
|
41 |
It achieves the following results on the evaluation set:
|
42 |
- eval_loss: 3.4220
|
43 |
- eval_runtime: 954.9678
|
|
|
48 |
|
49 |
## Model description
|
50 |
|
51 |
+
- Exploring to see how OPT does in terms of dialogue/conversational applications
|
52 |
+
- Seems to do a lot better than GPT-Neo with similar training parameters
|
53 |
|
54 |
## Intended uses & limitations
|
55 |
|
56 |
+
- OPT has a license that does not allow for commercial use, see original for details
|
57 |
+
- **any statements or claims made by this model do not reflect actual claims/statements by me**
|
58 |
|
59 |
## Training and evaluation data
|
60 |
|