Hugging Face's logo

danurahul
/
yoav_gpt_neo1.3B

Text Generation
Transformers
PyTorch
gpt_neo
Inference Endpoints
Model card Files Community
danurahul commited on
Commit
7ffe0d3
·
1 Parent(s): bc9a3dd

Initial commit

Browse files
Files changed (13) hide show
  1. config.json +73 -0
  2. merged.txt +0 -0
  3. merges.txt +0 -0
  4. optimizer.pt +3 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +1 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +1 -0
  11. trainer_state.json +22 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
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
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "embed_dropout": 0,
45
+ "eos_token_id": 50256,
46
+ "gradient_checkpointing": false,
47
+ "hidden_size": 2048,
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": null,
50
+ "layer_norm_epsilon": 1e-05,
51
+ "max_position_embeddings": 2048,
52
+ "model_type": "gpt_neo",
53
+ "num_heads": 16,
54
+ "num_layers": 24,
55
+ "resid_dropout": 0,
56
+ "summary_activation": null,
57
+ "summary_first_dropout": 0.1,
58
+ "summary_proj_to_labels": true,
59
+ "summary_type": "cls_index",
60
+ "summary_use_proj": true,
61
+ "task_specific_params": {
62
+ "text-generation": {
63
+ "do_sample": true,
64
+ "max_length": 50,
65
+ "temperature": 0.9
66
+ }
67
+ },
68
+ "tokenizer_class": "GPT2Tokenizer",
69
+ "transformers_version": "4.8.0.dev0",
70
+ "use_cache": true,
71
+ "vocab_size": 50257,
72
+ "window_size": 256
73
+ }
merged.txt ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8674beb71f39fca878c7e83fb9ce922cf1fe3ab8b47a177daa3048f0dfb15a
3
+ size 10524800795
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ca5c78967d65d82f241e47ce631d4cd7310ba947c36fdc50ac7e486a533f98
3
+ size 5312753383
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68033d1974e5abda6729494b3cba7ed2ae9e61b3ef514d09f74f0763ec301b8
3
+ size 13624
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f924049ee73e26f63f00845a4994184d3f3f6b82f4abbdbae5b1e3184d5e76c8
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-1.3B", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.1987281399046105,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.2,
12
+ "learning_rate": 4.006359300476948e-05,
13
+ "loss": 2.8434,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 2516,
18
+ "num_train_epochs": 1,
19
+ "total_flos": 4041448882176000.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9233ae77d31b3605693bb8dcdc9679909cf59420fa7508d174d07d98834042e5
3
+ size 2415
vocab.json ADDED
The diff for this file is too large to render. See raw diff