初始化项目，由ModelHub XC社区提供模型

Model: SimpleStories/SimpleStories-35M
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 +1,89 @@
+---
+license: mit
+datasets:
+- lennart-finke/SimpleStories
+language:
+- en
+tags:
+- small-language-model
+- story-generation
+- text-generation
+- efficient-nlp
+- distilled-models
+---
+
+# SimpleStories Model Family
+The SimpleStories models are a tiny model family created for interpretability research, trained on the [SimpleStories dataset](https://huggingface.co/datasets/lennart-finke/SimpleStories).
+
+## Usage
+
+```python
+import torch
+from transformers import AutoTokenizer, LlamaForCausalLM
+
+
+MODEL_SIZE = "35M"
+model_path = "SimpleStories/SimpleStories-{}".format(MODEL_SIZE)
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = LlamaForCausalLM.from_pretrained(model_path)
+model.to("cuda")
+model.eval()
+
+prompt = "The curious cat looked at the"
+
+inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
+input_ids = inputs.input_ids.to("cuda")
+
+eos_token_id = 1
+
+with torch.no_grad():
+    output_ids = model.generate(
+        input_ids=input_ids,
+        max_new_tokens=400,
+        temperature=0.7,
+        do_sample=True,
+        eos_token_id=eos_token_id
+)
+
+output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(f"\nGenerated text:\n{output_text}")
+
+```
+
+## Model Variants
+
+| Model Name | n_params | n_layers | d_model | n_heads | n_ctx | d_vocab |
+|------------|----------|----------|---------|---------|-------|---------|
+| SimpleStories-35M | 35 million | 12 | 512 | 8 | 512 | 4096 |
+| SimpleStories-30M | 30 million | 10 | 512 | 8 | 512 | 4096 |
+| SimpleStories-11M | 11 million | 6 | 384 | 6 | 512 | 4096 |
+| SimpleStories-5M | 5 million | 6 | 256 | 4 | 512 | 4096 |
+| SimpleStories-1.25M | 1.25 million | 4 | 128 | 4 | 512 | 4096 |
+
+## Performance Comparison
+Model-evaluated generation quality metrics:
+<p align="center">
+  <img width="80%" src="figures/simplestories_comparison.png">
+</p>
+
+
+## Tokenizer
+
+We use a custom WordPiece tokenizer with a small vocabulary size of 4096. We conducted morphological analysis and coverage gain analysis on the dataset
+to build a small tokenizer without compromising on the quality of generation.
+
+## Dataset
+
+The SimpleStories dataset is a collection of short stories generated by state-of-the-art language models. It features:
+
+- Story annotation with high-level concepts: theme, topic, style, etc.
+- Higher semantic and syntactic diversity through seeded story generation
+- Generated by 2024 models
+- Several NLP-metrics pre-computed to aid filtering
+- ASCII-only guarantee for the English dataset
+
+Read the dataset paper on [arXiv](https://arxiv.org/abs/2504.09184).
+
+## Training
+The training and evaluation scripts can be accessed at https://github.com/danbraunai/simple_stories_train

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1365,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 4096
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7460a77b46068632e5006754f936d1d0b2903f21f6a9ffe6d9fe043213b750
+size 140547880

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "[EOS]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}