Hugging Face's logo

tvergho
/
highlight_model

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
1
tvergho commited on
Commit
f59e37a
·
1 Parent(s): 7bd63d1

Model save

Browse files
Files changed (7) hide show
  1. config.json +7 -5
  2. pytorch_model.bin +2 -2
  3. runs/Jan29_20-55-48_5e46bb2b8a6f/1675025781.431266/events.out.tfevents.1675025781.5e46bb2b8a6f.327.1 +3 -0
  4. runs/Jan29_20-55-48_5e46bb2b8a6f/events.out.tfevents.1675025781.5e46bb2b8a6f.327.0 +3 -0
  5. runs/Jan29_20-55-48_5e46bb2b8a6f/events.out.tfevents.1675028637.5e46bb2b8a6f.327.2 +3 -0
  6. tokenizer_config.json +1 -1
  7. training_args.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -12,12 +12,14 @@
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
  "n_inner": null,
18
- "n_layer": 12,
19
  "n_positions": 1024,
 
20
  "pad_token_id": 50260,
 
21
  "reorder_and_upcast_attn": false,
22
  "resid_pdrop": 0.1,
23
  "scale_attn_by_inverse_layer_idx": false,
@@ -35,7 +37,7 @@
35
  }
36
  },
37
  "torch_dtype": "float32",
38
- "transformers_version": "4.26.0",
39
  "use_cache": true,
40
  "vocab_size": 50262
41
  }
 
1
  {
2
+ "_name_or_path": "gpt2-medium",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
  "n_inner": null,
18
+ "n_layer": 24,
19
  "n_positions": 1024,
20
+ "n_special": 0,
21
  "pad_token_id": 50260,
22
+ "predict_special_tokens": true,
23
  "reorder_and_upcast_attn": false,
24
  "resid_pdrop": 0.1,
25
  "scale_attn_by_inverse_layer_idx": false,
 
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.20.1",
41
  "use_cache": true,
42
  "vocab_size": 50262
43
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b871b6340c6da1c87856201bcacb464ac48d77cd1ef872647d42723910624f96
3
- size 510413373
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b3f664c2d2a0be6c23106e2eba9688dd34421e10b8716fffdd0ebad8fbda65
3
+ size 1444587353
runs/Jan29_20-55-48_5e46bb2b8a6f/1675025781.431266/events.out.tfevents.1675025781.5e46bb2b8a6f.327.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a01ae147d3ce56da839990e142de9ed4ad707b5194696c8a469428af4f44bd
3
+ size 5337
runs/Jan29_20-55-48_5e46bb2b8a6f/events.out.tfevents.1675025781.5e46bb2b8a6f.327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da473714d034231a81149fa21285f9ed55f5fd9fac80a7a042bd07e3992d2b64
3
+ size 5375
runs/Jan29_20-55-48_5e46bb2b8a6f/events.out.tfevents.1675028637.5e46bb2b8a6f.327.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983b379b751db52098d39f744dffacbdf55207fde3cffee64752e90ade9dc673
3
+ size 306
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
6
- "name_or_path": "gpt2",
7
  "special_tokens_map_file": null,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "unk_token": "<|endoftext|>"
 
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
6
+ "name_or_path": "gpt2-medium",
7
  "special_tokens_map_file": null,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "unk_token": "<|endoftext|>"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4178542ac5e13e0eeffce5bb1ffdec0735fdf919d0fe05b2b98a5a6f73de28ea
3
- size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb6c82bcb8363c00b89eec2cc483a93427a4f2365092d03c06b86781ea88711
3
+ size 3311