Hugging Face's logo

CharlesLi
/
OpenELM-1_1B-DPO-full-3-5

Text Generation
Transformers
TensorBoard
Safetensors
openelm
trl
dpo
Generated from Trainer
conversational
custom_code
Model card Files Metrics Community
CharlesLi commited on
Commit
4266022
•
1 Parent(s): b0db388

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. config.json +125 -0
  2. model.safetensors +3 -0
  3. runs/Aug30_10-22-23_xe8545-a100-10/events.out.tfevents.1725006682.xe8545-a100-10.535287.0 +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +43 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../../data/OpenELM-1_1B-SFT-3",
3
+ "activation_fn_name": "swish",
4
+ "architectures": [
5
+ "OpenELMForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_openelm.OpenELMConfig",
9
+ "AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "ffn_dim_divisor": 256,
14
+ "ffn_multipliers": [
15
+ 0.5,
16
+ 0.63,
17
+ 0.76,
18
+ 0.89,
19
+ 1.02,
20
+ 1.15,
21
+ 1.28,
22
+ 1.41,
23
+ 1.54,
24
+ 1.67,
25
+ 1.8,
26
+ 1.93,
27
+ 2.06,
28
+ 2.19,
29
+ 2.31,
30
+ 2.44,
31
+ 2.57,
32
+ 2.7,
33
+ 2.83,
34
+ 2.96,
35
+ 3.09,
36
+ 3.22,
37
+ 3.35,
38
+ 3.48,
39
+ 3.61,
40
+ 3.74,
41
+ 3.87,
42
+ 4.0
43
+ ],
44
+ "ffn_with_glu": true,
45
+ "head_dim": 64,
46
+ "initializer_range": 0.02,
47
+ "max_context_length": 2048,
48
+ "model_dim": 2048,
49
+ "model_type": "openelm",
50
+ "normalization_layer_name": "rms_norm",
51
+ "normalize_qk_projections": true,
52
+ "num_gqa_groups": 4,
53
+ "num_kv_heads": [
54
+ 4,
55
+ 4,
56
+ 4,
57
+ 5,
58
+ 5,
59
+ 5,
60
+ 5,
61
+ 5,
62
+ 5,
63
+ 5,
64
+ 6,
65
+ 6,
66
+ 6,
67
+ 6,
68
+ 6,
69
+ 6,
70
+ 6,
71
+ 6,
72
+ 7,
73
+ 7,
74
+ 7,
75
+ 7,
76
+ 7,
77
+ 7,
78
+ 8,
79
+ 8,
80
+ 8,
81
+ 8
82
+ ],
83
+ "num_query_heads": [
84
+ 16,
85
+ 16,
86
+ 16,
87
+ 20,
88
+ 20,
89
+ 20,
90
+ 20,
91
+ 20,
92
+ 20,
93
+ 20,
94
+ 24,
95
+ 24,
96
+ 24,
97
+ 24,
98
+ 24,
99
+ 24,
100
+ 24,
101
+ 24,
102
+ 28,
103
+ 28,
104
+ 28,
105
+ 28,
106
+ 28,
107
+ 28,
108
+ 32,
109
+ 32,
110
+ 32,
111
+ 32
112
+ ],
113
+ "num_transformer_layers": 28,
114
+ "qkv_multipliers": [
115
+ 0.5,
116
+ 1.0
117
+ ],
118
+ "rope_freq_constant": 10000,
119
+ "rope_max_length": 4096,
120
+ "share_input_output_layers": true,
121
+ "torch_dtype": "bfloat16",
122
+ "transformers_version": "4.44.2",
123
+ "use_cache": false,
124
+ "vocab_size": 32000
125
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b301491e2ce592afbb32899bcc59bb8eb0c6e785aa229682dcffe5ca9f2e5267
3
+ size 2159808696
runs/Aug30_10-22-23_xe8545-a100-10/events.out.tfevents.1725006682.xe8545-a100-10.535287.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4a8d986c90f6c1bf0a8c726dc439c19603071009020f1e9c7fb67ef3c00474
3
+ size 80464
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
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": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60bfbe87d029bef33f45ddc082d891c0f36968a4daa2f2813dbc1853d5f10c5
3
+ size 7544