BraylonDash commited on
Commit
c62da01
1 Parent(s): 1c4a63e

End of training

Browse files
Files changed (2) hide show
  1. README.md +5 -2
  2. config.json +26 -0
README.md CHANGED
@@ -1,10 +1,13 @@
1
  ---
2
  library_name: peft
3
  tags:
 
 
4
  - trl
5
  - dpo
6
- - generated_from_trainer
7
  base_model: DUAL-GPO/7b-kto-i0-merged
 
 
8
  model-index:
9
  - name: 7b-kto-10-40-i1
10
  results: []
@@ -15,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # 7b-kto-10-40-i1
17
 
18
- This model is a fine-tuned version of [DUAL-GPO/7b-kto-i0-merged](https://huggingface.co/DUAL-GPO/7b-kto-i0-merged) on the None dataset.
19
 
20
  ## Model description
21
 
 
1
  ---
2
  library_name: peft
3
  tags:
4
+ - alignment-handbook
5
+ - generated_from_trainer
6
  - trl
7
  - dpo
 
8
  base_model: DUAL-GPO/7b-kto-i0-merged
9
+ datasets:
10
+ - HuggingFaceH4/ultrafeedback_binarized
11
  model-index:
12
  - name: 7b-kto-10-40-i1
13
  results: []
 
18
 
19
  # 7b-kto-10-40-i1
20
 
21
+ This model is a fine-tuned version of [DUAL-GPO/7b-kto-i0-merged](https://huggingface.co/DUAL-GPO/7b-kto-i0-merged) on the HuggingFaceH4/ultrafeedback_binarized dataset.
22
 
23
  ## Model description
24
 
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DUAL-GPO/7b-kto-i0-merged",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.36.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }