Hugging Face's logo

BluebrainAI
/
parallel-mean-bottleneck-gpt2-medium-wikitext

Feature Extraction
Transformers
Safetensors
parallel-gpt2
Generated from Trainer
custom_code
Model card Files Community
shivanandmn commited on
Commit
47c6dfc
·
verified ·
1 Parent(s): e3a2c75

Training in progress, step 500

Browse files
Files changed (27) hide show
  1. .locks/models--gpt2-medium/1f1d9aaca301414e7f6c9396df506798ff4eb9a6.lock +0 -0
  2. .locks/models--gpt2-medium/226b0752cac7789c48f0cb3ec53eda48b7be36cc.lock +0 -0
  3. .locks/models--gpt2-medium/4b988bccc9dc5adacd403c00b4704976196548f8.lock +0 -0
  4. .locks/models--gpt2-medium/7b40acf43d912d857c663046ac178ee3fd7ff2d0.lock +0 -0
  5. .locks/models--gpt2-medium/be4d21d94f3b4687e5a54d84bf6ab46ed0f8defd.lock +0 -0
  6. config.json +45 -0
  7. merges.txt +0 -0
  8. model.safetensors +3 -0
  9. models--gpt2-medium/.no_exist/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/added_tokens.json +0 -0
  10. models--gpt2-medium/.no_exist/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/chat_template.jinja +0 -0
  11. models--gpt2-medium/.no_exist/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/special_tokens_map.json +0 -0
  12. models--gpt2-medium/blobs/1f1d9aaca301414e7f6c9396df506798ff4eb9a6 +0 -0
  13. models--gpt2-medium/blobs/226b0752cac7789c48f0cb3ec53eda48b7be36cc +0 -0
  14. models--gpt2-medium/blobs/4b988bccc9dc5adacd403c00b4704976196548f8 +0 -0
  15. models--gpt2-medium/blobs/7b40acf43d912d857c663046ac178ee3fd7ff2d0 +33 -0
  16. models--gpt2-medium/blobs/be4d21d94f3b4687e5a54d84bf6ab46ed0f8defd +1 -0
  17. models--gpt2-medium/refs/main +1 -0
  18. models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/config.json +33 -0
  19. models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/merges.txt +0 -0
  20. models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/tokenizer.json +0 -0
  21. models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/tokenizer_config.json +1 -0
  22. models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/vocab.json +0 -0
  23. special_tokens_map.json +5 -0
  24. tokenizer.json +0 -0
  25. tokenizer_config.json +21 -0
  26. training_args.bin +3 -0
  27. vocab.json +0 -0
.locks/models--gpt2-medium/1f1d9aaca301414e7f6c9396df506798ff4eb9a6.lock ADDED
File without changes
.locks/models--gpt2-medium/226b0752cac7789c48f0cb3ec53eda48b7be36cc.lock ADDED
File without changes
.locks/models--gpt2-medium/4b988bccc9dc5adacd403c00b4704976196548f8.lock ADDED
File without changes
.locks/models--gpt2-medium/7b40acf43d912d857c663046ac178ee3fd7ff2d0.lock ADDED
File without changes
.locks/models--gpt2-medium/be4d21d94f3b4687e5a54d84bf6ab46ed0f8defd.lock ADDED
File without changes
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "ParallelGPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "auto_map": {
8
+ "AutoConfig": "modeling_parallel_gpt2.ParallelGPT2Config",
9
+ "AutoModel": "modeling_parallel_gpt2.ParallelGPT2LMHeadModel"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "bottleneck_method": "mean",
13
+ "embd_pdrop": 0.1,
14
+ "eos_token_id": 50256,
15
+ "initializer_range": 0.02,
16
+ "layer_norm_epsilon": 1e-05,
17
+ "model_type": "parallel-gpt2",
18
+ "n_ctx": 1024,
19
+ "n_embd": 1024,
20
+ "n_head": 16,
21
+ "n_inner": null,
22
+ "n_layer": 24,
23
+ "n_positions": 1024,
24
+ "n_special": 0,
25
+ "predict_special_tokens": true,
26
+ "reorder_and_upcast_attn": false,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "summary_activation": null,
31
+ "summary_first_dropout": 0.1,
32
+ "summary_proj_to_labels": true,
33
+ "summary_type": "cls_index",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 50
39
+ }
40
+ },
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.49.0",
43
+ "use_cache": false,
44
+ "vocab_size": 50257
45
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6abefcf88f3ce3b998a407b476848777e5297132d6c98a0560cee3c2c431ce47
3
+ size 1419322880
models--gpt2-medium/.no_exist/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/added_tokens.json ADDED
File without changes
models--gpt2-medium/.no_exist/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/chat_template.jinja ADDED
File without changes
models--gpt2-medium/.no_exist/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/special_tokens_map.json ADDED
File without changes
models--gpt2-medium/blobs/1f1d9aaca301414e7f6c9396df506798ff4eb9a6 ADDED
The diff for this file is too large to render. See raw diff
 
models--gpt2-medium/blobs/226b0752cac7789c48f0cb3ec53eda48b7be36cc ADDED
The diff for this file is too large to render. See raw diff
 
models--gpt2-medium/blobs/4b988bccc9dc5adacd403c00b4704976196548f8 ADDED
The diff for this file is too large to render. See raw diff
 
models--gpt2-medium/blobs/7b40acf43d912d857c663046ac178ee3fd7ff2d0 ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 1024,
15
+ "n_head": 16,
16
+ "n_layer": 24,
17
+ "n_positions": 1024,
18
+ "n_special": 0,
19
+ "predict_special_tokens": true,
20
+ "resid_pdrop": 0.1,
21
+ "summary_activation": null,
22
+ "summary_first_dropout": 0.1,
23
+ "summary_proj_to_labels": true,
24
+ "summary_type": "cls_index",
25
+ "summary_use_proj": true,
26
+ "task_specific_params": {
27
+ "text-generation": {
28
+ "do_sample": true,
29
+ "max_length": 50
30
+ }
31
+ },
32
+ "vocab_size": 50257
33
+ }
models--gpt2-medium/blobs/be4d21d94f3b4687e5a54d84bf6ab46ed0f8defd ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 1024}
models--gpt2-medium/refs/main ADDED
@@ -0,0 +1 @@
 
 
1
+ 6dcaa7a952f72f9298047fd5137cd6e4f05f41da
models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 1024,
15
+ "n_head": 16,
16
+ "n_layer": 24,
17
+ "n_positions": 1024,
18
+ "n_special": 0,
19
+ "predict_special_tokens": true,
20
+ "resid_pdrop": 0.1,
21
+ "summary_activation": null,
22
+ "summary_first_dropout": 0.1,
23
+ "summary_proj_to_labels": true,
24
+ "summary_type": "cls_index",
25
+ "summary_use_proj": true,
26
+ "task_specific_params": {
27
+ "text-generation": {
28
+ "do_sample": true,
29
+ "max_length": 50
30
+ }
31
+ },
32
+ "vocab_size": 50257
33
+ }
models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 1024}
models--gpt2-medium/snapshots/6dcaa7a952f72f9298047fd5137cd6e4f05f41da/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>",
20
+ "use_fast": true
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2b5a7d39c37e8a28c3d381be80ab054db7b0e3e098fa7de7a0b88909dd67bf
3
+ size 5560
vocab.json ADDED
The diff for this file is too large to render. See raw diff