Hugging Face's logo

DatPySci
/
AR-Diff

Safetensors
Model card Files
xet
 Community
DatPySci commited on
Commit
6e72a0b
·
verified ·
1 Parent(s): 16f8bed

Delete models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process

Browse files
Files changed (7) hide show
  1. models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/chat_template.jinja +0 -1
  2. models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/config.json +0 -44
  3. models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/generation_config.json +0 -7
  4. models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/model.safetensors +0 -3
  5. models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/special_tokens_map.json +0 -38
  6. models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/tokenizer.json +0 -0
  7. models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/tokenizer_config.json +0 -143
models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/chat_template.jinja DELETED
@@ -1 +0,0 @@
1
- {% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}
 
 
models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/config.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 2,
8
- "dtype": "bfloat16",
9
- "eos_token_id": 3,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 768,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_types": [
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention"
28
- ],
29
- "max_position_embeddings": 2048,
30
- "max_window_layers": 24,
31
- "model_type": "qwen3",
32
- "num_attention_heads": 12,
33
- "num_hidden_layers": 12,
34
- "num_key_value_heads": 2,
35
- "rms_norm_eps": 1e-06,
36
- "rope_scaling": null,
37
- "rope_theta": 1000000.0,
38
- "sliding_window": null,
39
- "tie_word_embeddings": true,
40
- "transformers_version": "4.57.6",
41
- "use_cache": false,
42
- "use_sliding_window": false,
43
- "vocab_size": 2200
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 2,
4
- "eos_token_id": 3,
5
- "transformers_version": "4.57.6",
6
- "use_cache": false
7
- }
 
 
 
 
 
 
 
 
models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e8105a1012413cd5e7b13c289b4d177ae6dcca7fe9d22b373992fbe28d7b3aa
3
- size 239368216
 
 
 
 
models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/special_tokens_map.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<question>",
4
- "</question>",
5
- "<solution>",
6
- "</solution>",
7
- "<answer>",
8
- "</answer>"
9
- ],
10
- "bos_token": {
11
- "content": "[BOS]",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- "eos_token": {
18
- "content": "[EOS]",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "[PAD]",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- "unk_token": {
32
- "content": "[UNK]",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- }
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
models/RL/composition/Qwen3-100M-AR-0.999zoo_op2-20+0.001teacher_op2-process/tokenizer_config.json DELETED
@@ -1,143 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "[UNK]",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "[PAD]",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "[BOS]",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "[EOS]",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<question>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "</question>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "6": {
53
- "content": "<solution>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "7": {
61
- "content": "</solution>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "8": {
69
- "content": "<answer>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "9": {
77
- "content": "</answer>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "2196": {
85
- "content": "<special_token_0>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "2197": {
93
- "content": "<special_token_1>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "2198": {
101
- "content": "<special_token_2>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "2199": {
109
- "content": "<special_token_3>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "2200": {
117
- "content": "<special_token_4>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- }
124
- },
125
- "additional_special_tokens": [
126
- "<question>",
127
- "</question>",
128
- "<solution>",
129
- "</solution>",
130
- "<answer>",
131
- "</answer>"
132
- ],
133
- "bos_token": "[BOS]",
134
- "clean_up_tokenization_spaces": false,
135
- "eos_token": "[EOS]",
136
- "extra_special_tokens": {},
137
- "model_max_length": 1000000000000000019884624838656,
138
- "pad_token": "[PAD]",
139
- "padding_side": "right",
140
- "split_special_tokens": false,
141
- "tokenizer_class": "PreTrainedTokenizerFast",
142
- "unk_token": "[UNK]"
143
- }