Hugging Face's logo

BeardedMonster
/
traffic

Text Generation
Transformers
Safetensors
gpt2
Inference Endpoints
text-generation-inference
Model card Files Community
BeardedMonster commited on
Commit
0fd01b8
•
1 Parent(s): a4c2c76

Upload GPTNeoXForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +22 -33
  2. generation_config.json +2 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,41 +1,30 @@
1
  {
2
- "_name_or_path": "cti_report_summarizer",
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": 1024,
16
- "n_head": 16,
17
- "n_inner": null,
18
- "n_layer": 24,
19
- "n_positions": 1024,
20
- "n_special": 0,
21
- "predict_special_tokens": true,
22
- "reorder_and_upcast_attn": false,
23
- "resid_pdrop": 0.1,
24
- "scale_attn_by_inverse_layer_idx": false,
25
- "scale_attn_weights": true,
26
- "summary_activation": null,
27
- "summary_first_dropout": 0.1,
28
- "summary_proj_to_labels": true,
29
- "summary_type": "cls_index",
30
- "summary_use_proj": true,
31
- "task_specific_params": {
32
- "text-generation": {
33
- "do_sample": true,
34
- "max_length": 50
35
- }
36
- },
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.40.1",
39
  "use_cache": true,
40
- "vocab_size": 50257
 
41
  }
 
1
  {
2
+ "_name_or_path": "EleutherAI/pythia-410m",
 
3
  "architectures": [
4
+ "GPTNeoXForCausalLM"
5
  ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
  "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.40.1",
27
  "use_cache": true,
28
+ "use_parallel_residual": true,
29
+ "vocab_size": 50304
30
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
  "transformers_version": "4.40.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
  "transformers_version": "4.40.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24f0004c0d216f6b8636d65a80416a7cfbd6c78eaa4870d7c7a3dfc694da7a6c
3
- size 1419322880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642a7e14b0bc1b9a18009a17cb3a9bf4e602b3a25aeb0cd9d66e48844fdced96
3
+ size 1621370224