Hugging Face's logo

xiulinyang
/
dynamic_attention_10M

TensorBoard
Safetensors
gpt2
Model card Files
xet
Metrics Community
xiulinyang commited on
Commit
fe516c6
·
verified ·
1 Parent(s): 282c88e

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. all_results.json +1 -0
  2. best_checkpoint/model.safetensors +3 -0
  3. best_checkpoint/optimizer.bin +3 -0
  4. best_checkpoint/random_states_0.pkl +3 -0
  5. best_checkpoint/scheduler.bin +3 -0
  6. config.json +32 -0
  7. events.out.tfevents.1761428421.489ab9961314.18847.0 +3 -0
  8. generation_config.json +6 -0
  9. model.safetensors +3 -0
  10. special_tokens_map.json +23 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +59 -0
all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 23.446472754160723}
best_checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce38387a6e75bb2b86a0c66963de1b73959ac21e1309c577f66c6288f3ba505
3
+ size 47254888
best_checkpoint/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340b58be4a231067dccdd9c165e84554e53a257bd0e604131f15fbe25b2ccbc5
3
+ size 94543115
best_checkpoint/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662cf35fab040c346263210503744ea97999834b527efa89ba5890f99a27ce76
3
+ size 14821
best_checkpoint/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fcd912e08a464cfbdff1230b9b1fd09bb1356e95394ba53fa93728c2ad90aa
3
+ size 1465
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 32769,
8
+ "cache_dir": "./hf_cache",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 32770,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 256,
15
+ "n_head": 4,
16
+ "n_inner": null,
17
+ "n_layer": 4,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.46.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 32776
32
+ }
events.out.tfevents.1761428421.489ab9961314.18847.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c66f827cad2bbf61fce6f1e45ebb4c886d28e12c71757d0a1476260ff1b055
3
+ size 225
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32769,
4
+ "eos_token_id": 32770,
5
+ "transformers_version": "4.46.0.dev0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce38387a6e75bb2b86a0c66963de1b73959ac21e1309c577f66c6288f3ba505
3
+ size 47254888
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[EOS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32768": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32769": {
36
+ "content": "[BOS]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32770": {
44
+ "content": "[EOS]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "[BOS]",
53
+ "cache_dir": "./hf_cache",
54
+ "clean_up_tokenization_spaces": false,
55
+ "eos_token": "[EOS]",
56
+ "model_max_length": 1000000000000000019884624838656,
57
+ "pad_token": "[PAD]",
58
+ "tokenizer_class": "PreTrainedTokenizerFast"
59
+ }