ZhangShenao
commited on
Commit
•
0b50e35
1
Parent(s):
0c5f708
End of training
Browse files- README.md +8 -1
- config.json +1 -1
README.md
CHANGED
@@ -2,9 +2,16 @@
|
|
2 |
license: mit
|
3 |
base_model: microsoft/Phi-3-mini-4k-instruct
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: 0.001_SELM-Phi-3-mini-4k-instruct_iter_1
|
10 |
results: []
|
@@ -15,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# 0.001_SELM-Phi-3-mini-4k-instruct_iter_1
|
17 |
|
18 |
-
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
2 |
license: mit
|
3 |
base_model: microsoft/Phi-3-mini-4k-instruct
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
9 |
+
- trl
|
10 |
+
- dpo
|
11 |
+
- generated_from_trainer
|
12 |
+
datasets:
|
13 |
+
- updated
|
14 |
+
- original
|
15 |
model-index:
|
16 |
- name: 0.001_SELM-Phi-3-mini-4k-instruct_iter_1
|
17 |
results: []
|
|
|
22 |
|
23 |
# 0.001_SELM-Phi-3-mini-4k-instruct_iter_1
|
24 |
|
25 |
+
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the updated and the original datasets.
|
26 |
|
27 |
## Model description
|
28 |
|
config.json
CHANGED
@@ -30,6 +30,6 @@
|
|
30 |
"tie_word_embeddings": false,
|
31 |
"torch_dtype": "bfloat16",
|
32 |
"transformers_version": "4.40.2",
|
33 |
-
"use_cache":
|
34 |
"vocab_size": 32064
|
35 |
}
|
|
|
30 |
"tie_word_embeddings": false,
|
31 |
"torch_dtype": "bfloat16",
|
32 |
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
"vocab_size": 32064
|
35 |
}
|