File size: 4,947 Bytes
b84d85a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #!/usr/bin/env python3
"""
Prepare Codsworth for HuggingFace Upload
Creates proper HF-compatible format
"""
import json
import os
import shutil
import torch
import sys
sys.path.insert(0, '.')
from codsworth.config import CodsworthConfig
from codsworth.model import CodsworthTransformer
def prepare_for_huggingface(
model_path: str = "codsworth_model.pt",
tokenizer_path: str = "tokenizer.json",
output_dir: str = "hf_upload",
):
"""Prepare files in HuggingFace format"""
print(f"Preparing files in {output_dir}/")
# Create output directory
os.makedirs(output_dir, exist_ok=True)
# 1. Copy model weights
print("Copying model weights...")
shutil.copy(model_path, f"{output_dir}/pytorch_model.bin")
# 2. Copy tokenizer
print("Copying tokenizer...")
shutil.copy(tokenizer_path, f"{output_dir}/tokenizer.json")
# 3. Create HuggingFace config.json
print("Creating config.json...")
hf_config = {
"model_type": "codsworth",
"architectures": ["CodsworthTransformer"],
"vocab_size": 5004,
"hidden_size": 256,
"num_hidden_layers": 2,
"num_attention_heads": 4,
"head_dim": 64,
"intermediate_size": 512,
"max_position_embeddings": 128,
"rope_theta": 10000.0,
"use_rope": True,
"hidden_dropout": 0.1,
"attention_dropout": 0.0,
"pad_token_id": 0,
"bos_token_id": 1,
"eos_token_id": 2,
"torch_dtype": "float32",
"transformers_version": "4.0.0",
}
with open(f"{output_dir}/config.json", 'w') as f:
json.dump(hf_config, f, indent=2)
# 4. Create tokenizer_config.json
print("Creating tokenizer_config.json...")
tokenizer_config = {
"added_tokens_decoder": {
"0": {"content": "<pad>", "single_word": False, "lstrip": False, "rstrip": False, "normalized": False, "special": True},
"1": {"content": "<unk>", "single_word": False, "lstrip": False, "rstrip": False, "normalized": False, "special": True},
"2": {"content": "<bos>", "single_word": False, "lstrip": False, "rstrip": False, "normalized": False, "special": True},
"3": {"content": "<eos>", "single_word": False, "lstrip": False, "rstrip": False, "normalized": False, "special": True}
},
"bos_token": "<bos>",
"eos_token": "<eos>",
"pad_token": "<pad>",
"unk_token": "<unk>",
"model_max_length": 128,
"tokenizer_class": "PreTrainedTokenizer",
}
with open(f"{output_dir}/tokenizer_config.json", 'w') as f:
json.dump(tokenizer_config, f, indent=2)
# 5. Create README.md (model card)
print("Creating README.md...")
readme = """---
license: mit
tags:
- transformer
- language-model
- pytorch
- decoder-only
---
# Codsworth
A small transformer language model built from scratch in PyTorch.
## Model Details
- **Parameters**: ~3.9M
- **Architecture**: GPT-style decoder-only transformer
- **Position Encoding**: RoPE (Rotary Position Embedding)
- **Activation**: SwiGLU
## Usage
```python
import torch
import json
from huggingface_hub import hf_hub_download
# Download files
model_path = hf_hub_download(repo_id="your-username/codsworth", filename="pytorch_model.bin")
tokenizer_path = hf_hub_download(repo_id="your-username/codsworth", filename="tokenizer.json")
config_path = hf_hub_download(repo_id="your-username/codsworth", filename="config.json")
# Load using codsworth library
import sys
sys.path.insert(0, 'path/to/codsworth')
from codsworth.config import CodsworthConfig
from codsworth.model import CodsworthTransformer
with open(config_path) as f:
cfg = json.load(f)
model_cfg = cfg["model"]
config = CodsworthConfig(**model_cfg)
model = CodsworthTransformer(config)
model.load_state_dict(torch.load(model_path))
# Generate
input_ids = torch.tensor([[1, 2, 3]])
output = model.generate(input_ids, max_new_tokens=20)
print(output)
```
"""
with open(f"{output_dir}/README.md", 'w') as f:
f.write(readme)
print(f"\n✓ Files prepared in {output_dir}/")
print("\nFiles:")
for f in os.listdir(output_dir):
size = os.path.getsize(f"{output_dir}/{f}")
print(f" - {f} ({size/1024:.1f} KB)")
print("\n" + "=" * 50)
print("To upload to HuggingFace:")
print("=" * 50)
print(f"""
Option 1 - Using huggingface-cli:
huggingface-cli upload-repo your-username/codsworth
Option 2 - Using Python:
pip install huggingface_hub
python -c "
from huggingface_hub import HfApi
api = HfApi()
api.upload_folder(
folder_path='{output_dir}',
repo_id='your-username/codsworth',
repo_type='model'
)
"
Option 3 - Manual:
1. Go to https://huggingface.co/new
2. Create repo 'codsworth'
3. Upload files from {output_dir}/
""")
if __name__ == "__main__":
prepare_for_huggingface() |