martimfasantos commited on
Commit
c237ae5
1 Parent(s): f2e2a3a

End of training

Browse files
Files changed (2) hide show
  1. README.md +7 -1
  2. config.json +1 -1
README.md CHANGED
@@ -2,9 +2,15 @@
2
  license: apache-2.0
3
  base_model: martimfasantos/tinyllama-1.1b-mt-sft-full
4
  tags:
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
 
 
 
 
 
8
  model-index:
9
  - name: tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
10
  results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
17
 
18
- This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-mt-sft-full](https://huggingface.co/martimfasantos/tinyllama-1.1b-mt-sft-full) on the None dataset.
19
 
20
  ## Model description
21
 
 
2
  license: apache-2.0
3
  base_model: martimfasantos/tinyllama-1.1b-mt-sft-full
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
+ - trl
10
+ - dpo
11
+ - generated_from_trainer
12
+ datasets:
13
+ - haoranxu/ALMA-R-Preference
14
  model-index:
15
  - name: tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
16
  results: []
 
21
 
22
  # tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
23
 
24
+ This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-mt-sft-full](https://huggingface.co/martimfasantos/tinyllama-1.1b-mt-sft-full) on the haoranxu/ALMA-R-Preference dataset.
25
 
26
  ## Model description
27
 
config.json CHANGED
@@ -24,6 +24,6 @@
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.41.2",
27
- "use_cache": false,
28
  "vocab_size": 32000
29
  }
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.41.2",
27
+ "use_cache": true,
28
  "vocab_size": 32000
29
  }