Hugging Face's logo

helloadhavan
/
llara2-100M-base

Safetensors
English
gpt2
from-scratch
Model card Files
xet
 Community
Skyrocknroll commited on
Commit
8bc3171
·
1 Parent(s): 38e1956

init

Browse files
Files changed (24) hide show
  1. gpt_wiki_ctx764_scratch_out/checkpoint-45000/config.json +35 -0
  2. gpt_wiki_ctx764_scratch_out/checkpoint-45000/generation_config.json +9 -0
  3. gpt_wiki_ctx764_scratch_out/checkpoint-45000/model.safetensors +3 -0
  4. gpt_wiki_ctx764_scratch_out/checkpoint-45000/optimizer.pt +3 -0
  5. gpt_wiki_ctx764_scratch_out/checkpoint-45000/rng_state.pth +3 -0
  6. gpt_wiki_ctx764_scratch_out/checkpoint-45000/scaler.pt +3 -0
  7. gpt_wiki_ctx764_scratch_out/checkpoint-45000/scheduler.pt +3 -0
  8. gpt_wiki_ctx764_scratch_out/checkpoint-45000/trainer_state.json +0 -0
  9. gpt_wiki_ctx764_scratch_out/checkpoint-45000/training_args.bin +3 -0
  10. gpt_wiki_ctx764_scratch_out/checkpoint-49000/config.json +35 -0
  11. gpt_wiki_ctx764_scratch_out/checkpoint-49000/generation_config.json +9 -0
  12. gpt_wiki_ctx764_scratch_out/checkpoint-49000/model.safetensors +3 -0
  13. gpt_wiki_ctx764_scratch_out/checkpoint-49000/optimizer.pt +3 -0
  14. gpt_wiki_ctx764_scratch_out/checkpoint-49000/rng_state.pth +3 -0
  15. gpt_wiki_ctx764_scratch_out/checkpoint-49000/scaler.pt +3 -0
  16. gpt_wiki_ctx764_scratch_out/checkpoint-49000/scheduler.pt +3 -0
  17. gpt_wiki_ctx764_scratch_out/checkpoint-49000/trainer_state.json +0 -0
  18. gpt_wiki_ctx764_scratch_out/checkpoint-49000/training_args.bin +3 -0
  19. gpt_wiki_ctx764_scratch_out/config.json +35 -0
  20. gpt_wiki_ctx764_scratch_out/generation_config.json +9 -0
  21. gpt_wiki_ctx764_scratch_out/model.safetensors +3 -0
  22. gpt_wiki_ctx764_scratch_out/tokenizer.json +0 -0
  23. gpt_wiki_ctx764_scratch_out/tokenizer_config.json +13 -0
  24. gpt_wiki_ctx764_scratch_out/training_args.bin +3 -0
gpt_wiki_ctx764_scratch_out/checkpoint-45000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 764,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 764,
21
+ "pad_token_id": 50256,
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
+ "tie_word_embeddings": true,
32
+ "transformers_version": "5.12.1",
33
+ "use_cache": false,
34
+ "vocab_size": 50257
35
+ }
gpt_wiki_ctx764_scratch_out/checkpoint-45000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.12.1",
8
+ "use_cache": true
9
+ }
gpt_wiki_ctx764_scratch_out/checkpoint-45000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f02b13d143875138d511f9bfca822d4893e4b6c00604fb807bdf669cbacce5
3
+ size 496975488
gpt_wiki_ctx764_scratch_out/checkpoint-45000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e4a6c38b0a070f5f9903d8e323012651848acfd2c898dd15e41b2fddd9e01c
3
+ size 994044858
gpt_wiki_ctx764_scratch_out/checkpoint-45000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1ab3137303ff37cabe42963732b15b902a89b6071d00084ec6e09dd39fd802
3
+ size 14244
gpt_wiki_ctx764_scratch_out/checkpoint-45000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb0d19d9590700884f77bafc8c29417ad57082b8c36522c18d8e188f8b38c84
3
+ size 988
gpt_wiki_ctx764_scratch_out/checkpoint-45000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7d003a281d187b69d478a0da55d827ce014113e8fe11a610134891e1cbb8a2
3
+ size 1064
gpt_wiki_ctx764_scratch_out/checkpoint-45000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
gpt_wiki_ctx764_scratch_out/checkpoint-45000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d567c033e1a786ead8b31ac7079215a2854d25ab829c2cc186f067f6edb02b6a
3
+ size 4728
gpt_wiki_ctx764_scratch_out/checkpoint-49000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 764,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 764,
21
+ "pad_token_id": 50256,
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
+ "tie_word_embeddings": true,
32
+ "transformers_version": "5.12.1",
33
+ "use_cache": false,
34
+ "vocab_size": 50257
35
+ }
gpt_wiki_ctx764_scratch_out/checkpoint-49000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.12.1",
8
+ "use_cache": true
9
+ }
gpt_wiki_ctx764_scratch_out/checkpoint-49000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aeb2e4f8b70b76984f2a61b73de0c7dc253142a586689cde92bcedc3aa784f8
3
+ size 496975488
gpt_wiki_ctx764_scratch_out/checkpoint-49000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd09c46754c7076afa7659a1ce3de1d9747dd084ca5011d3b34207015d49540
3
+ size 994044858
gpt_wiki_ctx764_scratch_out/checkpoint-49000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf5770c4f03d0988011a9cab0a63f7904050f2e2606880638976b151ff3c56e
3
+ size 14244
gpt_wiki_ctx764_scratch_out/checkpoint-49000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c1b10dfc066afd86b7384a6d3c5f93de502ecbdd29944771cba70eceb39166
3
+ size 988
gpt_wiki_ctx764_scratch_out/checkpoint-49000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff106eff7d816c8988e34dcb308d3738e45f51edc3ebf53d06e737ac24821d6
3
+ size 1064
gpt_wiki_ctx764_scratch_out/checkpoint-49000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
gpt_wiki_ctx764_scratch_out/checkpoint-49000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d567c033e1a786ead8b31ac7079215a2854d25ab829c2cc186f067f6edb02b6a
3
+ size 4728
gpt_wiki_ctx764_scratch_out/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 764,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 764,
21
+ "pad_token_id": 50256,
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
+ "tie_word_embeddings": true,
32
+ "transformers_version": "5.12.1",
33
+ "use_cache": false,
34
+ "vocab_size": 50257
35
+ }
gpt_wiki_ctx764_scratch_out/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.12.1",
8
+ "use_cache": true
9
+ }
gpt_wiki_ctx764_scratch_out/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aeb2e4f8b70b76984f2a61b73de0c7dc253142a586689cde92bcedc3aa784f8
3
+ size 496975488
gpt_wiki_ctx764_scratch_out/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
gpt_wiki_ctx764_scratch_out/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
gpt_wiki_ctx764_scratch_out/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d567c033e1a786ead8b31ac7079215a2854d25ab829c2cc186f067f6edb02b6a
3
+ size 4728