Hugging Face's logo

Kkoustubh
/
QuoteGPT

Text Generation
Transformers
TensorFlow
gpt2
generated_from_keras_callback
Model card Files
xet
 Community
Kkoustubh commited on
Commit
0e61dfe
·
1 Parent(s): ae276a9

Training in progress epoch 0

Browse files
Files changed (9) hide show
  1. README.md +6 -8
  2. config.json +22 -10
  3. generation_config.json +2 -0
  4. merges.txt +0 -0
  5. special_tokens_map.json +4 -2
  6. tf_model.h5 +2 -2
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +6 -3
  9. vocab.json +0 -0
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: mit
3
  tags:
4
  - generated_from_keras_callback
5
  model-index:
@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
12
 
13
  # Kkoustubh/QuoteGPT
14
 
15
- This model is a fine-tuned version of [openai-gpt](https://huggingface.co/openai-gpt) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 2.0536
18
- - Validation Loss: 1.9668
19
- - Epoch: 2
20
 
21
  ## Model description
22
 
@@ -42,9 +42,7 @@ The following hyperparameters were used during training:
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
- | 2.1816 | 2.0752 | 0 |
46
- | 2.1098 | 2.0075 | 1 |
47
- | 2.0536 | 1.9668 | 2 |
48
 
49
 
50
  ### Framework versions
 
1
  ---
2
+ license: apache-2.0
3
  tags:
4
  - generated_from_keras_callback
5
  model-index:
 
12
 
13
  # Kkoustubh/QuoteGPT
14
 
15
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.2943
18
+ - Validation Loss: 1.9411
19
+ - Epoch: 0
20
 
21
  ## Model description
22
 
 
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 2.2943 | 1.9411 | 0 |
 
 
46
 
47
 
48
  ### Framework versions
config.json CHANGED
@@ -1,22 +1,33 @@
1
  {
2
- "_name_or_path": "openai-gpt",
3
- "afn": "gelu",
 
4
  "architectures": [
5
- "OpenAIGPTLMHeadModel"
6
  ],
7
  "attn_pdrop": 0.1,
 
8
  "embd_pdrop": 0.1,
 
 
 
 
9
  "initializer_range": 0.02,
 
 
 
10
  "layer_norm_epsilon": 1e-05,
11
- "model_type": "openai-gpt",
12
- "n_ctx": 512,
13
  "n_embd": 768,
14
  "n_head": 12,
15
- "n_layer": 12,
16
- "n_positions": 512,
17
- "n_special": 0,
18
- "predict_special_tokens": true,
19
  "resid_pdrop": 0.1,
 
 
20
  "summary_activation": null,
21
  "summary_first_dropout": 0.1,
22
  "summary_proj_to_labels": true,
@@ -29,5 +40,6 @@
29
  }
30
  },
31
  "transformers_version": "4.30.1",
32
- "vocab_size": 40478
 
33
  }
 
1
  {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
  "architectures": [
6
+ "GPT2LMHeadModel"
7
  ],
8
  "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
  "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
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": 1024,
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,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
  "summary_activation": null,
32
  "summary_first_dropout": 0.1,
33
  "summary_proj_to_labels": true,
 
40
  }
41
  },
42
  "transformers_version": "4.30.1",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
  }
generation_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
  "_from_model_config": true,
 
 
3
  "transformers_version": "4.30.1"
4
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
  "transformers_version": "4.30.1"
6
  }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
- "pad_token": "[PAD]",
3
- "unk_token": "<unk>"
 
 
4
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afc3048b86a4afdf5964561539f55383ce8f34aa7d79c3b0b047bdf3fb7b83cf
3
- size 466313552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713e0b63f2ac73a1f4ee044117950992fa8ed6a1973f0ae4e7690e492a52a824
3
+ size 327745472
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,9 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "model_max_length": 512,
4
- "tokenizer_class": "OpenAIGPTTokenizer",
5
- "unk_token": "<unk>"
 
6
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
  "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff