nnheui commited on
Commit
6970dba
1 Parent(s): d8e1435

End of training

Browse files
Files changed (2) hide show
  1. README.md +4 -1
  2. config.json +41 -0
README.md CHANGED
@@ -2,10 +2,13 @@
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: zephyr-7b-kto-qlora
11
  results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # zephyr-7b-kto-qlora
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 an unknown dataset.
20
 
21
  ## Model description
22
 
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
  base_model: alignment-handbook/zephyr-7b-sft-full
10
+ datasets:
11
+ - HuggingFaceH4/ultrafeedback_binarized
12
  model-index:
13
  - name: zephyr-7b-kto-qlora
14
  results: []
 
19
 
20
  # zephyr-7b-kto-qlora
21
 
22
+ 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 HuggingFaceH4/ultrafeedback_binarized dataset.
23
 
24
  ## Model description
25
 
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
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
+ "quantization_config": {
19
+ "_load_in_4bit": true,
20
+ "_load_in_8bit": false,
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_storage": "uint8",
23
+ "bnb_4bit_quant_type": "nf4",
24
+ "bnb_4bit_use_double_quant": false,
25
+ "llm_int8_enable_fp32_cpu_offload": false,
26
+ "llm_int8_has_fp16_weight": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_theta": 10000.0,
35
+ "sliding_window": 4096,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.39.3",
39
+ "use_cache": true,
40
+ "vocab_size": 32000
41
+ }