Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+- storytelling
+- fiction
+- tiny-stories
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Athspi LLM
+
+🧠 A small but capable language model for creative story generation, trained on the TinyStories dataset.
+
+![Athspi Banner](https://example.com/banner.jpg) <!-- Add your banner image URL -->
+
+## Model Details
+
+### Architecture
+- **Model Type**: Transformer-based language model
+- **Layers**: 4
+- **Embedding Dim**: 384
+- **Heads**: 6
+- **Sequence Length**: 128 tokens
+- **Parameters**: ~28M
+
+### Training Data
+- **Dataset**: [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories)
+- **Training Coverage**: 5% of dataset (~100k samples)
+
+## Usage
+
+### Installation
+```bash
+pip install torch transformers sentencepiece

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 384,
+  "n_head": 6,
+  "n_inner": null,
+  "n_layer": 4,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fe5ad3c74e10a6898d9b379132b5bdd9772413b54ef90018936c9df04303ef
+size 183001177

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": 129,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}