Hugging Face's logo

ZainAli60
/
test

Text Generation
Transformers
Safetensors
gpt_neo
Model card Files
xet
Community
ZainAli60 commited on
Commit
238194a
·
verified ·
1 Parent(s): f53afc4

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +20 -47
  2. generation_config.json +2 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,55 +1,28 @@
1
  {
2
- "_name_or_path": "/workspace/pretraining/local-models/training/2024-03-14_01-54-04",
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": "4.38.0",
52
  "use_cache": true,
53
- "vocab_size": 50257,
54
- "window_size": 256
55
  }
 
1
  {
2
+ "_name_or_path": "/root/pretraining/local-models/training/2024-03-21_17-11-02",
 
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 6112,
14
+ "max_position_embeddings": 1024,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 12,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
 
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.38.0",
26
  "use_cache": true,
27
+ "vocab_size": 50257
 
28
  }
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": "4.38.0"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
  "transformers_version": "4.38.0"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9ad17949921ddabb9eec1b9e2b954000a8537522ea17785ebd6c4d30ebf7947
3
- size 500811336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9bb408675d16e1922dcf2ce25395b20be0c641a5019093b6bec792d8b9f0d3
3
+ size 3079115120