YYYYYYibo commited on
Commit
45e2643
1 Parent(s): f9aa23f

DPO-7b-beta0.01

Browse files
Files changed (1) hide show
  1. README.md +6 -2
README.md CHANGED
@@ -2,10 +2,14 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - dpo
7
- - generated_from_trainer
8
  base_model: alignment-handbook/zephyr-7b-sft-full
 
 
 
9
  model-index:
10
  - name: nash_dpo_doff_no_golden_iter_1
11
  results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # nash_dpo_doff_no_golden_iter_1
18
 
19
- This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
  - Logits/chosen: -2.7444
22
  - Logits/rejected: -2.6646
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
  - trl
8
  - dpo
 
9
  base_model: alignment-handbook/zephyr-7b-sft-full
10
+ datasets:
11
+ - updated
12
+ - original
13
  model-index:
14
  - name: nash_dpo_doff_no_golden_iter_1
15
  results: []
 
20
 
21
  # nash_dpo_doff_no_golden_iter_1
22
 
23
+ This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the updated and the original datasets.
24
  It achieves the following results on the evaluation set:
25
  - Logits/chosen: -2.7444
26
  - Logits/rejected: -2.6646