Hugging Face's logo

Tatbooy
/
llm-course-hw2-reward-model

Text Classification
Transformers
Safetensors
llama
Generated from Trainer
trl
reward-trainer
text-generation-inference
Model card Files
xet
Community
Tatbooy commited on
Commit
6605076
·
verified ·
1 Parent(s): dc54a7b

Tatbooy/llm-course-hw2-reward-model

Browse files
Files changed (6) hide show
  1. README.md +4 -4
  2. config.json +36 -36
  3. model.safetensors +2 -2
  4. special_tokens_map.json +28 -28
  5. tokenizer_config.json +155 -155
  6. training_args.bin +1 -1
README.md CHANGED
@@ -36,9 +36,9 @@ This model was trained with Reward.
36
  ### Framework versions
37
 
38
  - TRL: 0.16.0
39
- - Transformers: 4.50.0
40
- - Pytorch: 2.6.0+cu124
41
- - Datasets: 3.5.0
42
  - Tokenizers: 0.21.1
43
 
44
  ## Citations
@@ -50,7 +50,7 @@ Cite TRL as:
50
  ```bibtex
51
  @misc{vonwerra2022trl,
52
  title = {{TRL: Transformer Reinforcement Learning}},
53
- author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
54
  year = 2020,
55
  journal = {GitHub repository},
56
  publisher = {GitHub},
 
36
  ### Framework versions
37
 
38
  - TRL: 0.16.0
39
+ - Transformers: 4.50.2
40
+ - Pytorch: 2.6.0+cu118
41
+ - Datasets: 3.3.2
42
  - Tokenizers: 0.21.1
43
 
44
  ## Citations
 
50
  ```bibtex
51
  @misc{vonwerra2022trl,
52
  title = {{TRL: Transformer Reinforcement Learning}},
53
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin GallouГ©dec},
54
  year = 2020,
55
  journal = {GitHub repository},
56
  publisher = {GitHub},
config.json CHANGED
@@ -1,36 +1,36 @@
1
- {
2
- "architectures": [
3
- "LlamaForSequenceClassification"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "head_dim": 64,
10
- "hidden_act": "silu",
11
- "hidden_size": 576,
12
- "id2label": {
13
- "0": "LABEL_0"
14
- },
15
- "initializer_range": 0.02,
16
- "intermediate_size": 1536,
17
- "label2id": {
18
- "LABEL_0": 0
19
- },
20
- "max_position_embeddings": 2048,
21
- "mlp_bias": false,
22
- "model_type": "llama",
23
- "num_attention_heads": 9,
24
- "num_hidden_layers": 30,
25
- "num_key_value_heads": 3,
26
- "pad_token_id": 2,
27
- "pretraining_tp": 1,
28
- "rms_norm_eps": 1e-05,
29
- "rope_scaling": null,
30
- "rope_theta": 10000.0,
31
- "tie_word_embeddings": true,
32
- "torch_dtype": "bfloat16",
33
- "transformers_version": "4.50.0",
34
- "use_cache": true,
35
- "vocab_size": 49152
36
- }
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 576,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "max_position_embeddings": 2048,
21
+ "mlp_bias": false,
22
+ "model_type": "llama",
23
+ "num_attention_heads": 9,
24
+ "num_hidden_layers": 30,
25
+ "num_key_value_heads": 3,
26
+ "pad_token_id": 2,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": null,
30
+ "rope_theta": 10000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.50.2",
34
+ "use_cache": true,
35
+ "vocab_size": 49152
36
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff9977982cead3f03e3ae5a7393c307b69623f93e282dc7b9b48215baa26b8b5
3
- size 269061784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250aea1d1bf7c21aa49e040949bde8a221c99cc8dd3f0e5b4bc6a19d85aae0c6
3
+ size 538092792
special_tokens_map.json CHANGED
@@ -1,28 +1,28 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>"
5
- ],
6
- "bos_token": {
7
- "content": "<|im_start|>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "eos_token": {
14
- "content": "<|im_end|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "pad_token": "<|im_end|>",
21
- "unk_token": {
22
- "content": "<|endoftext|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false
27
- }
28
- }
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer_config.json CHANGED
@@ -1,155 +1,155 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<repo_name>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<reponame>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<file_sep>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "6": {
53
- "content": "<filename>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "7": {
61
- "content": "<gh_stars>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "8": {
69
- "content": "<issue_start>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "9": {
77
- "content": "<issue_comment>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "10": {
85
- "content": "<issue_closed>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "11": {
93
- "content": "<jupyter_start>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "12": {
101
- "content": "<jupyter_text>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "13": {
109
- "content": "<jupyter_code>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "14": {
117
- "content": "<jupyter_output>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "15": {
125
- "content": "<jupyter_script>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "16": {
133
- "content": "<empty_output>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- }
140
- },
141
- "additional_special_tokens": [
142
- "<|im_start|>",
143
- "<|im_end|>"
144
- ],
145
- "bos_token": "<|im_start|>",
146
- "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
- "clean_up_tokenization_spaces": false,
148
- "eos_token": "<|im_end|>",
149
- "extra_special_tokens": {},
150
- "model_max_length": 2048,
151
- "pad_token": "<|im_end|>",
152
- "tokenizer_class": "GPT2Tokenizer",
153
- "unk_token": "<|endoftext|>",
154
- "vocab_size": 49152
155
- }
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "extra_special_tokens": {},
150
+ "model_max_length": 2048,
151
+ "pad_token": "<|im_end|>",
152
+ "tokenizer_class": "GPT2Tokenizer",
153
+ "unk_token": "<|endoftext|>",
154
+ "vocab_size": 49152
155
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6251355e49b3905f8376993707034959b89dc4c566d5ede9a82c3f5325ecd581
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a15ed4cf4ca3cd7397a8725ed8d692c9b340a6573c0bf6aef1dc32a6a3d92c
3
  size 5432