Hugging Face's logo

Trelis
/
OpenELM-270M-instruct-ORPO

Text Generation
Transformers
Safetensors
openelm
apple
OpenELM
conversational
custom_code
Model card Files
xet
Community
RonanMcGovern commited on
Commit
8a9655c
·
verified ·
1 Parent(s): 30d8495

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +89 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +42 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "apple/OpenELM-270M-instruct",
3
+ "activation_fn_name": "swish",
4
+ "architectures": [
5
+ "OpenELMForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "apple/OpenELM-270M-instruct--configuration_openelm.OpenELMConfig",
9
+ "AutoModelForCausalLM": "apple/OpenELM-270M-instruct--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
+ 0.73,
17
+ 0.97,
18
+ 1.2,
19
+ 1.43,
20
+ 1.67,
21
+ 1.9,
22
+ 2.13,
23
+ 2.37,
24
+ 2.6,
25
+ 2.83,
26
+ 3.07,
27
+ 3.3,
28
+ 3.53,
29
+ 3.77,
30
+ 4.0
31
+ ],
32
+ "ffn_with_glu": true,
33
+ "head_dim": 64,
34
+ "initializer_range": 0.02,
35
+ "max_context_length": 2048,
36
+ "model_dim": 1280,
37
+ "model_type": "openelm",
38
+ "normalization_layer_name": "rms_norm",
39
+ "normalize_qk_projections": true,
40
+ "num_gqa_groups": 4,
41
+ "num_kv_heads": [
42
+ 3,
43
+ 3,
44
+ 3,
45
+ 3,
46
+ 3,
47
+ 4,
48
+ 4,
49
+ 4,
50
+ 4,
51
+ 4,
52
+ 4,
53
+ 4,
54
+ 5,
55
+ 5,
56
+ 5,
57
+ 5
58
+ ],
59
+ "num_query_heads": [
60
+ 12,
61
+ 12,
62
+ 12,
63
+ 12,
64
+ 12,
65
+ 16,
66
+ 16,
67
+ 16,
68
+ 16,
69
+ 16,
70
+ 16,
71
+ 16,
72
+ 20,
73
+ 20,
74
+ 20,
75
+ 20
76
+ ],
77
+ "num_transformer_layers": 16,
78
+ "qkv_multipliers": [
79
+ 0.5,
80
+ 1.0
81
+ ],
82
+ "rope_freq_constant": 10000,
83
+ "rope_max_length": 4096,
84
+ "share_input_output_layers": true,
85
+ "torch_dtype": "bfloat16",
86
+ "transformers_version": "4.40.1",
87
+ "use_cache": true,
88
+ "vocab_size": 32000
89
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.40.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2175a15862d699f989cf52463b28ab5544005bc94275e4c9aeeb7da449d69e3
3
+ size 543068952
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% if messages[0]['role'] == 'user' %}{{ bos_token }}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "left",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fafcdde7eff75bbf861b7b323e97dff393f451d446c7a8e7bea87821f70572e1
3
+ size 5304