Hugging Face's logo

DancingIguana
/
codeparrot-ds

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
DancingIguana commited on
Commit
cdb892d
•
1 Parent(s): 885df73

End of training

Browse files
Files changed (8) hide show
  1. config.json +10 -3
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. runs/Jun11_16-49-48_4366ac95dc97/1654966412.217843/events.out.tfevents.1654966412.4366ac95dc97.71.1 +3 -0
  5. runs/Jun11_16-49-48_4366ac95dc97/events.out.tfevents.1654966412.4366ac95dc97.71.0 +3 -0
  6. tokenizer.json +0 -0
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
config.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
- "_name_or_path": "gpt2",
 
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -8,14 +9,20 @@
8
  "bos_token_id": 0,
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 0,
 
 
 
11
  "initializer_range": 0.02,
 
 
 
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 128,
15
  "n_embd": 768,
16
  "n_head": 12,
17
  "n_inner": null,
18
- "n_layer": 12,
19
  "n_positions": 1024,
20
  "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
@@ -35,5 +42,5 @@
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.19.4",
37
  "use_cache": true,
38
- "vocab_size": 49
39
  }
 
1
  {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
  "activation_function": "gelu_new",
5
  "architectures": [
6
  "GPT2LMHeadModel"
 
9
  "bos_token_id": 0,
10
  "embd_pdrop": 0.1,
11
  "eos_token_id": 0,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
  "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
  "layer_norm_epsilon": 1e-05,
20
  "model_type": "gpt2",
21
  "n_ctx": 128,
22
  "n_embd": 768,
23
  "n_head": 12,
24
  "n_inner": null,
25
+ "n_layer": 6,
26
  "n_positions": 1024,
27
  "reorder_and_upcast_attn": false,
28
  "resid_pdrop": 0.1,
 
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.19.4",
44
  "use_cache": true,
45
+ "vocab_size": 25000
46
  }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28240473f8c99804a0cf25ab9d4f5b9a78a898d8f451e3f67c00b7a7feca811e
3
- size 356157545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f19947bc84435921c713126f060abfae30fd5505d0a980cb30e27108c4daf04
3
+ size 256379613
runs/Jun11_16-49-48_4366ac95dc97/1654966412.217843/events.out.tfevents.1654966412.4366ac95dc97.71.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8334a5ed5d07935140b0cc076ed58db211e69847c0970384064028aff4e2ea1c
3
+ size 5150
runs/Jun11_16-49-48_4366ac95dc97/events.out.tfevents.1654966412.4366ac95dc97.71.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78dd7a92a378f9a82b11592c20bb20c44428bebd384b3b496b03c7099ea5043
3
+ size 4182
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0436b2ed813b8ba3e8d830b36a61ad4f1346332cbd191e8d642cdcac207465b7
3
  size 3183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b64d9f3a1b4f17235e48e59c8c601848addff803519a54aeb8cae3805e5bf32
3
  size 3183
vocab.json CHANGED
The diff for this file is too large to render. See raw diff