Hugging Face's logo

ZeusCabanas
/
GPT-bi

Text Generation
Transformers
Safetensors
Basque
gpt2
text-generation-inference
Model card Files
xet
 Community
ZeusCabanas commited on
Commit
d728a9b
·
verified ·
1 Parent(s): 7b41e35

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. README.md +8 -1
  2. checkpoint-100000/config.json +32 -0
  3. checkpoint-100000/generation_config.json +6 -0
  4. checkpoint-100000/model.safetensors +3 -0
  5. checkpoint-100000/optimizer.pt +3 -0
  6. checkpoint-100000/rng_state.pth +3 -0
  7. checkpoint-100000/scheduler.pt +3 -0
  8. checkpoint-100000/trainer_state.json +0 -0
  9. checkpoint-100000/training_args.bin +3 -0
  10. checkpoint-96000/config.json +32 -0
  11. checkpoint-96000/generation_config.json +6 -0
  12. checkpoint-96000/model.safetensors +3 -0
  13. checkpoint-96000/optimizer.pt +3 -0
  14. checkpoint-96000/rng_state.pth +3 -0
  15. checkpoint-96000/scheduler.pt +3 -0
  16. checkpoint-96000/trainer_state.json +0 -0
  17. checkpoint-96000/training_args.bin +3 -0
  18. checkpoint-98000/config.json +32 -0
  19. checkpoint-98000/generation_config.json +6 -0
  20. checkpoint-98000/model.safetensors +3 -0
  21. checkpoint-98000/optimizer.pt +3 -0
  22. checkpoint-98000/rng_state.pth +3 -0
  23. checkpoint-98000/scheduler.pt +3 -0
  24. checkpoint-98000/trainer_state.json +0 -0
  25. checkpoint-98000/training_args.bin +3 -0
  26. config.json +32 -0
  27. generation_config.json +6 -0
  28. model.safetensors +3 -0
README.md CHANGED
@@ -1,6 +1,13 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
 
 
 
 
 
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: transformers
3
+ license: mit
4
+ datasets:
5
+ - HiTZ/latxa-corpus-v1.1
6
+ language:
7
+ - eu
8
+ base_model:
9
+ - openai-community/gpt2
10
+ pipeline_tag: text-generation
11
  ---
12
 
13
  # Model Card for Model ID
checkpoint-100000/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": 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": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
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": "4.48.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32000
32
+ }
checkpoint-100000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.48.2"
6
+ }
checkpoint-100000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0eccacfc82427cf944adcee42eb6b71d7f7dd22fb31ccbe14c5c0658667d6f
3
+ size 441688704
checkpoint-100000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5f7255e0faec873e2deba5b041ca9020961bbb5ea33455fdb8d178e783a064
3
+ size 883471290
checkpoint-100000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65b83de08af91bcda90a4ede4a78d1cb6afce7ce07d3ef1cf0e9f230212624f
3
+ size 14244
checkpoint-100000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dce3bf2d2f03cb5495a5e5a2b3721309e04149c82ddbbb1d8c8f575370ad0db
3
+ size 1064
checkpoint-100000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee38d4579253b52c46e368e36bf5fcbd4564ac994a18fa1271ee1c757b0a75c
3
+ size 5304
checkpoint-96000/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": 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": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
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": "4.48.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32000
32
+ }
checkpoint-96000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.48.2"
6
+ }
checkpoint-96000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7846e30da6b564f7a3436b1ecbcb7d72568b74e7e902c492797f28547b901591
3
+ size 441688704
checkpoint-96000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16d8322ec75b89eb5d84f2ada3b88b929833971dd2c395a0a34d831e30d9965
3
+ size 883471290
checkpoint-96000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27338eeea0cb466e443e49cf3c747ac6188c0fe231cc43e4882d9ebb922fbb37
3
+ size 14244
checkpoint-96000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e97a4871fde7634d54bb72580f1c2e91f6a574ee3d4f0ed390c935446379f2
3
+ size 1064
checkpoint-96000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-96000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee38d4579253b52c46e368e36bf5fcbd4564ac994a18fa1271ee1c757b0a75c
3
+ size 5304
checkpoint-98000/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": 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": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
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": "4.48.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32000
32
+ }
checkpoint-98000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.48.2"
6
+ }
checkpoint-98000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b0a5e699388239c97d55ec0931f005da2ab48ba2ec996f623324e9be90e923
3
+ size 441688704
checkpoint-98000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8356d8eafebabb0484dc3f87561c02a6174da3130d3b7dab8294e17513d11284
3
+ size 883471290
checkpoint-98000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c59f146edf4947ab2d5245925b3c28167a6ace1e1e26123c6c26a171a44fd8
3
+ size 14244
checkpoint-98000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4485acf2e582d464dac87cf839b2db6e3f42982a856689cc1f13bce24d4e30e
3
+ size 1064
checkpoint-98000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-98000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee38d4579253b52c46e368e36bf5fcbd4564ac994a18fa1271ee1c757b0a75c
3
+ size 5304
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": 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": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
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": "4.48.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32000
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.48.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0eccacfc82427cf944adcee42eb6b71d7f7dd22fb31ccbe14c5c0658667d6f
3
+ size 441688704