Hugging Face's logo

joshcarp
/
gpt2-evy

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Community
joshcarp commited on
Commit
03cb668
•
1 Parent(s): d90da68

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. config.json +31 -81
  2. model.safetensors +2 -2
  3. special_tokens_map.json +4 -21
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +11 -32
config.json CHANGED
@@ -1,89 +1,39 @@
1
  {
2
- "_name_or_path": "apple/OpenELM-270M",
3
- "activation_fn_name": "swish",
4
  "architectures": [
5
- "OpenELMForCausalLM"
6
  ],
7
- "auto_map": {
8
- "AutoConfig": "apple/OpenELM-270M--configuration_openelm.OpenELMConfig",
9
- "AutoModelForCausalLM": "apple/OpenELM-270M--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": "float32",
86
  "transformers_version": "4.40.1",
87
  "use_cache": true,
88
- "vocab_size": 32000
89
  }
 
1
  {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.40.1",
37
  "use_cache": true,
38
+ "vocab_size": 50257
39
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b298fe0eccc100e5eaeef718146a438b34ee56527c209b4d46193a3fc73ad183
3
- size 1086123184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94f6e9cffb51e060ec27aa65373d7bfb12cfeaf8f1f2e406484444ca16ad06b
3
+ size 497774208
special_tokens_map.json CHANGED
@@ -1,23 +1,6 @@
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
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,41 +1,20 @@
1
  {
2
- "add_bos_token": true,
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
- "clean_up_tokenization_spaces": false,
32
- "eos_token": "</s>",
33
- "legacy": false,
34
- "model_max_length": 1000000000000000019884624838656,
35
- "pad_token": null,
36
- "padding_side": "right",
37
- "sp_model_kwargs": {},
38
- "tokenizer_class": "LlamaTokenizer",
39
- "unk_token": "<unk>",
40
- "use_default_system_prompt": false
41
  }
 
1
  {
2
+ "add_prefix_space": false,
 
3
  "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
+ "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
 
 
 
 
20
  }