100m-sftd-python / README.md
Ananda100's picture
Upload folder using huggingface_hub
82bdbd0 verified
|
Raw
History Blame Contribute Delete
925 Bytes
metadata
license: apache-2.0
tags:
  - nanoGPT
  - code-generation
  - fine-tuned
base_model: Ananda100/pocketcoder100M-distilled

100m-sftd-python

Full-parameter fine-tune of Ananda100/pocketcoder100M-distilled on a custom Python coding-problem dataset, using the deepseek-ai/deepseek-coder-6.7b-base tokenizer.

  • Fine-tune tokens processed: 356,253,696
  • Best validation loss: 0.9270
  • Held-out pass@1: 9.5%
  • Block size: 512
  • Vocab size: 32022

Loading

This is a custom architecture, not a native transformers model, so AutoModel.from_pretrained won't work out of the box:

import json, torch
from safetensors.torch import load_file

with open("config.json") as f:
    cfg = json.load(f)

config = GPTConfig(**cfg)
model = GPT(config)
state_dict = load_file("model.safetensors")
model.load_state_dict(state_dict)
model.eval()