Hugging Face's logo

Pushkar27
/
GriceBench-DPO

Text Generation
PEFT
Safetensors
English
dialogue
gricean-maxims
cooperative-communication
lora
dpo
direct-preference-optimization
gpt2
nlp
Eval Results (legacy)
Model card Files
xet
 Community
Pushkar27 commited on
Commit
927ca3b
·
verified ·
1 Parent(s): c85d941

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. adapter_config.json +36 -36
  2. history (1).json +27 -0
  3. special_tokens_map.json +6 -6
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +21 -21
adapter_config.json CHANGED
@@ -1,37 +1,37 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "gpt2-medium",
5
- "bias": "none",
6
- "corda_config": null,
7
- "eva_config": null,
8
- "exclude_modules": null,
9
- "fan_in_fan_out": true,
10
- "inference_mode": true,
11
- "init_lora_weights": true,
12
- "layer_replication": null,
13
- "layers_pattern": null,
14
- "layers_to_transform": null,
15
- "loftq_config": {},
16
- "lora_alpha": 32,
17
- "lora_bias": false,
18
- "lora_dropout": 0.05,
19
- "megatron_config": null,
20
- "megatron_core": "megatron.core",
21
- "modules_to_save": null,
22
- "peft_type": "LORA",
23
- "qalora_group_size": 16,
24
- "r": 16,
25
- "rank_pattern": {},
26
- "revision": null,
27
- "target_modules": [
28
- "c_proj",
29
- "c_attn",
30
- "c_fc"
31
- ],
32
- "task_type": "CAUSAL_LM",
33
- "trainable_token_indices": null,
34
- "use_dora": false,
35
- "use_qalora": false,
36
- "use_rslora": false
37
  }
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gpt2-medium",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "c_proj",
29
+ "c_attn",
30
+ "c_fc"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_qalora": false,
36
+ "use_rslora": false
37
  }
history (1).json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train_loss": [
3
+ 0.028017110751970165,
4
+ 0.013388305872224913,
5
+ 0.008757742770432215
6
+ ],
7
+ "maxim_losses": [
8
+ {
9
+ "quantity": 0.03399555156678718,
10
+ "quality": 0.015326214804867197,
11
+ "relation": 0.016142378936564256,
12
+ "manner": 0.04562233979931943
13
+ },
14
+ {
15
+ "quantity": 0.015276468253982853,
16
+ "quality": 0.008590008613421832,
17
+ "relation": 0.006301149650273589,
18
+ "manner": 0.02251838400279205
19
+ },
20
+ {
21
+ "quantity": 0.009361670283496682,
22
+ "quality": 0.0064510579641700394,
23
+ "relation": 0.003563862554918086,
24
+ "manner": 0.014890103049689744
25
+ }
26
+ ]
27
+ }
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
6
- }
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,21 +1,21 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- }
12
- },
13
- "bos_token": "<|endoftext|>",
14
- "clean_up_tokenization_spaces": false,
15
- "eos_token": "<|endoftext|>",
16
- "extra_special_tokens": {},
17
- "model_max_length": 1024,
18
- "pad_token": "<|endoftext|>",
19
- "tokenizer_class": "GPT2Tokenizer",
20
- "unk_token": "<|endoftext|>"
21
- }
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }