Hugging Face's logo

PhilSad
/
lucie-7b-GRPO-science-long-thinking-boxed-accuracy

Safetensors
Model card Files
xet
 Community
PhilSad commited on
Commit
27f4d81
·
verified ·
1 Parent(s): d564fdf

Training in progress, step 10

Browse files
Files changed (7) hide show
  1. adapter_config.json +34 -0
  2. adapter_model.safetensors +3 -0
  3. chat_template.jinja +11 -0
  4. special_tokens_map.json +35 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +81 -0
  7. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "PhilSad/Lucie-7B-GRPO-Science-500",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
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": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "trainable_token_indices": null,
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464fd1c5f68bebe536bc2feac1e5293ef99f4c807a4eba13ab40e83a653374b4
3
+ size 13648432
chat_template.jinja ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- for message in messages %}
3
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>
4
+
5
+ '+ message['content'] | trim + '<|eot_id|>' }}
6
+ {%- endfor %}
7
+ {%- if add_generation_prompt %}
8
+ {{- '<|start_header_id|>assistant<|end_header_id|>
9
+
10
+ ' }}
11
+ {%- endif %}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|start_header_id|>",
4
+ "<|end_header_id|>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|eot_id|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<pad>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "265": {
39
+ "content": "<|start_header_id|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "266": {
47
+ "content": "<|end_header_id|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "267": {
55
+ "content": "<|eot_id|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ }
62
+ },
63
+ "additional_special_tokens": [
64
+ "<|start_header_id|>",
65
+ "<|end_header_id|>",
66
+ "</s>"
67
+ ],
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "<|eot_id|>",
71
+ "extra_special_tokens": {},
72
+ "legacy": true,
73
+ "model_max_length": 1000000000000000000000000000000,
74
+ "pad_token": "<pad>",
75
+ "padding_side": "left",
76
+ "sp_model_kwargs": {},
77
+ "spaces_between_special_tokens": false,
78
+ "tokenizer_class": "LlamaTokenizerFast",
79
+ "unk_token": "<unk>",
80
+ "use_default_system_prompt": false
81
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffed3ce4254496ec0776a81d22e91b52f3161dcd3890d6c683ceaab7255400b
3
+ size 6865