Hugging Face's logo

vitaliy-sharandin
/
wiseai

Text Generation
Transformers
PyTorch
Safetensors
English
llama
mental-health
psychology
llm
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
vitaliy-sharandin commited on
Commit
89bb3ba
·
1 Parent(s): 1c0f90d

Upload GPTNeoForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +39 -23
  2. generation_config.json +4 -5
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,39 +1,55 @@
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": "4.29.1",
37
  "use_cache": true,
38
- "vocab_size": 50257
 
39
  }
 
1
  {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
  ],
 
31
  "bos_token_id": 50256,
32
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
  "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
  "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
  "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
 
 
 
 
 
 
45
  "summary_activation": null,
46
  "summary_first_dropout": 0.1,
47
  "summary_proj_to_labels": true,
48
  "summary_type": "cls_index",
49
  "summary_use_proj": true,
 
 
 
 
 
 
50
  "torch_dtype": "float32",
51
+ "transformers_version": "4.29.2",
52
  "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
  }
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
- "early_stopping": true,
3
- "max_length": 50,
4
- "no_repeat_ngram_size": 2,
5
- "num_beams": 5,
6
- "transformers_version": "4.29.1"
7
  }
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.29.2"
 
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93b783dbfbdfe4cb37d7dd5ae5ed476a1880ae866edb355a59477cc66860f316
3
- size 510395581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7b412eee10a7c7a2bb4090efbfe7a4c7d384f8514209d8f9a1c66ac7104671
3
+ size 551184237