初始化项目，由ModelHub XC社区提供模型

Model: Abdourakib/tinystories-gpt2-124m
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+
+---
+language: en
+tags:
+- gpt2
+- text-generation
+- children-stories
+- tinystories
+license: mit
+---
+
+# TinyStories GPT2 124M
+
+A GPT2 model trained from scratch on the 
+TinyStories dataset to generate children's stories.
+
+## Training Details
+- **Base Architecture:** GPT2 (124M parameters)
+- **Dataset:** karpathy/tinystories-gpt4-clean
+- **Training Steps:** 100,000
+- **Best Val Loss:** 1.1295
+- **Hardware:** NVIDIA RTX PRO 6000 (G4)
+
+## How To Use
+```python
+from transformers import GPT2LMHeadModel
+from transformers import GPT2TokenizerFast
+import torch
+
+model = GPT2LMHeadModel.from_pretrained(
+    "{HF_USERNAME}/{MODEL_NAME}"
+)
+tokenizer = GPT2TokenizerFast.from_pretrained(
+    "{HF_USERNAME}/{MODEL_NAME}"
+)
+
+prompt = "Once upon a time there was a little cat"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+outputs = model.generate(
+    inputs["input_ids"],
+    max_new_tokens     = 200,
+    temperature        = 0.8,
+    top_p              = 0.9,
+    do_sample          = True,
+    repetition_penalty = 1.2,
+    pad_token_id       = tokenizer.eos_token_id
+)
+
+story = tokenizer.decode(
+    outputs[0],
+    skip_special_tokens = True
+)
+print(story)
+```
+
+## Example Output
+
+"Once upon a time there was a little cat called 
+Mimi. She loved to play with her toys, but one 
+day she got very sad because she couldn't find 
+her favorite toy. They searched everywhere and 
+finally found it under the bed! Mimi was so 
+happy and hugged her mom tight."
+
+## Limitations
+- Generates children's stories only
+- Works best with story-style prompts
+- 512 token context window

config.json

@@ -0,0 +1,36 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": null,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51ad2e5281c3136057571454a30ae9ca1084a6224986b7b31e7d515bb3f6244
+size 496225920

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}