RedMist137
commited on
Commit
•
be374ad
1
Parent(s):
e11b85e
End of training
Browse files- README.md +7 -1
- config.json +1 -1
README.md
CHANGED
@@ -2,9 +2,15 @@
|
|
2 |
license: other
|
3 |
base_model: facebook/opt-2.7b
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: DPO-Zephyr-7B
|
10 |
results: []
|
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# DPO-Zephyr-7B
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) on the
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
2 |
license: other
|
3 |
base_model: facebook/opt-2.7b
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
9 |
+
- trl
|
10 |
+
- dpo
|
11 |
+
- generated_from_trainer
|
12 |
+
datasets:
|
13 |
+
- RedMist137/AIHF_DPO_iter0
|
14 |
model-index:
|
15 |
- name: DPO-Zephyr-7B
|
16 |
results: []
|
|
|
21 |
|
22 |
# DPO-Zephyr-7B
|
23 |
|
24 |
+
This model is a fine-tuned version of [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) on the RedMist137/AIHF_DPO_iter0 dataset.
|
25 |
|
26 |
## Model description
|
27 |
|
config.json
CHANGED
@@ -25,7 +25,7 @@
|
|
25 |
"prefix": "</s>",
|
26 |
"torch_dtype": "bfloat16",
|
27 |
"transformers_version": "4.40.2",
|
28 |
-
"use_cache":
|
29 |
"vocab_size": 50272,
|
30 |
"word_embed_proj_dim": 2560
|
31 |
}
|
|
|
25 |
"prefix": "</s>",
|
26 |
"torch_dtype": "bfloat16",
|
27 |
"transformers_version": "4.40.2",
|
28 |
+
"use_cache": true,
|
29 |
"vocab_size": 50272,
|
30 |
"word_embed_proj_dim": 2560
|
31 |
}
|