Hugging Face's logo

PolyakovMaxim
/
ModelGptTS

Text Generation
Transformers
PyTorch
JAX
gpt2
text-generation-inference
Model card Files
xet
 Community
1
PolyakovMaxim commited on
Commit
be57f22
·
1 Parent(s): cfc7868

new

Browse files
Files changed (7) hide show
  1. config.json +5 -8
  2. eval_results.txt +1 -1
  3. merges.txt +0 -0
  4. pytorch_model.bin +2 -2
  5. tokenizer_config.json +1 -1
  6. training_args.bin +2 -2
  7. vocab.json +0 -0
config.json CHANGED
@@ -13,6 +13,7 @@
13
  "embd_pdrop": 0.1,
14
  "eos_token_id": 50256,
15
  "finetuning_task": null,
 
16
  "id2label": {
17
  "0": "LABEL_0",
18
  "1": "LABEL_1"
@@ -29,11 +30,12 @@
29
  "max_length": 20,
30
  "min_length": 0,
31
  "model_type": "gpt2",
32
- "n_ctx": 1024,
33
  "n_embd": 768,
34
  "n_head": 12,
 
35
  "n_layer": 12,
36
- "n_positions": 1024,
37
  "no_repeat_ngram_size": 0,
38
  "num_beams": 1,
39
  "num_return_sequences": 1,
@@ -50,12 +52,7 @@
50
  "summary_proj_to_labels": true,
51
  "summary_type": "cls_index",
52
  "summary_use_proj": true,
53
- "task_specific_params": {
54
- "text-generation": {
55
- "do_sample": true,
56
- "max_length": 50
57
- }
58
- },
59
  "temperature": 1.0,
60
  "top_k": 50,
61
  "top_p": 1.0,
 
13
  "embd_pdrop": 0.1,
14
  "eos_token_id": 50256,
15
  "finetuning_task": null,
16
+ "gradient_checkpointing": false,
17
  "id2label": {
18
  "0": "LABEL_0",
19
  "1": "LABEL_1"
 
30
  "max_length": 20,
31
  "min_length": 0,
32
  "model_type": "gpt2",
33
+ "n_ctx": 2048,
34
  "n_embd": 768,
35
  "n_head": 12,
36
+ "n_inner": null,
37
  "n_layer": 12,
38
+ "n_positions": 2048,
39
  "no_repeat_ngram_size": 0,
40
  "num_beams": 1,
41
  "num_return_sequences": 1,
 
52
  "summary_proj_to_labels": true,
53
  "summary_type": "cls_index",
54
  "summary_use_proj": true,
55
+ "task_specific_params": null,
 
 
 
 
 
56
  "temperature": 1.0,
57
  "top_k": 50,
58
  "top_p": 1.0,
eval_results.txt CHANGED
@@ -1 +1 @@
1
- perplexity = tensor(2.5974)
 
1
+ perplexity = tensor(10.0303)
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 sha256:5fc9368fcc3cccd4e93d4b32a371f09bbe83f0215d8f40193e82b20d4cc2959a
3
- size 548150575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:436507365fca523a5c1f809b096577fea92c2cb6e3f356fa3fc213d5b9555b5a
3
+ size 702291247
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"max_len": 1024}
 
1
+ {}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44806ab939e9ed746a636de25845e9c28917a370de455b4c95019a6b4a18e61a
3
- size 1519
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bfc76c16bd248e15b8457f55aeaa60a47d32d714c5b4f0b8adeb7cf8d20f1c
3
+ size 1583
vocab.json CHANGED
The diff for this file is too large to render. See raw diff