YYYYYYibo commited on
Commit
b2ee730
1 Parent(s): 389395f

DPO-7b-beta0.01

Browse files
Files changed (2) hide show
  1. README.md +9 -1
  2. config.json +1 -1
README.md CHANGED
@@ -1,8 +1,16 @@
1
  ---
 
2
  tags:
 
3
  - trl
4
  - dpo
5
  - generated_from_trainer
 
 
 
 
 
 
6
  model-index:
7
  - name: gshf_ours_1_iter_3
8
  results: []
@@ -13,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # gshf_ours_1_iter_3
15
 
16
- This model was trained from scratch on the None dataset.
17
 
18
  ## Model description
19
 
 
1
  ---
2
+ base_model: model/gshf_ours_1_iter_2
3
  tags:
4
+ - alignment-handbook
5
  - trl
6
  - dpo
7
  - generated_from_trainer
8
+ - trl
9
+ - dpo
10
+ - generated_from_trainer
11
+ datasets:
12
+ - updated
13
+ - original
14
  model-index:
15
  - name: gshf_ours_1_iter_3
16
  results: []
 
21
 
22
  # gshf_ours_1_iter_3
23
 
24
+ This model is a fine-tuned version of [model/gshf_ours_1_iter_2](https://huggingface.co/model/gshf_ours_1_iter_2) on the updated and the original datasets.
25
 
26
  ## Model description
27
 
config.json CHANGED
@@ -21,6 +21,6 @@
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.38.2",
24
- "use_cache": false,
25
  "vocab_size": 32000
26
  }
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
  "vocab_size": 32000
26
  }