Athagi commited on
Commit
72bbd12
·
verified ·
1 Parent(s): 7fe5783

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. README.md +36 -0
  2. config.json +38 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. tokenizer_config.json +28 -0
  6. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ - storytelling
6
+ - fiction
7
+ - tiny-stories
8
+ pipeline_tag: text-generation
9
+ library_name: transformers
10
+ ---
11
+
12
+ # Athspi LLM
13
+
14
+ 🧠 A small but capable language model for creative story generation, trained on the TinyStories dataset.
15
+
16
+ ![Athspi Banner](https://example.com/banner.jpg) <!-- Add your banner image URL -->
17
+
18
+ ## Model Details
19
+
20
+ ### Architecture
21
+ - **Model Type**: Transformer-based language model
22
+ - **Layers**: 4
23
+ - **Embedding Dim**: 384
24
+ - **Heads**: 6
25
+ - **Sequence Length**: 128 tokens
26
+ - **Parameters**: ~28M
27
+
28
+ ### Training Data
29
+ - **Dataset**: [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories)
30
+ - **Training Coverage**: 5% of dataset (~100k samples)
31
+
32
+ ## Usage
33
+
34
+ ### Installation
35
+ ```bash
36
+ pip install torch transformers sentencepiece
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 384,
16
+ "n_head": 6,
17
+ "n_inner": null,
18
+ "n_layer": 4,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "transformers_version": "4.47.1",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fe5ad3c74e10a6898d9b379132b5bdd9772413b54ef90018936c9df04303ef
3
+ size 183001177
tokenizer_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "max_length": 129,
18
+ "model_max_length": 1024,
19
+ "pad_to_multiple_of": null,
20
+ "pad_token": "<|endoftext|>",
21
+ "pad_token_type_id": 0,
22
+ "padding_side": "right",
23
+ "stride": 0,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "truncation_side": "right",
26
+ "truncation_strategy": "longest_first",
27
+ "unk_token": "<|endoftext|>"
28
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff