iamtarun/python_code_instructions_18k_alpaca
Viewer • Updated • 18.6k • 29.3k • 347
How to use Vo1dAbyss/DeepSeek-R1-Distill-Qwen-7B-Python-4bit with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Vo1dAbyss/DeepSeek-R1-Distill-Qwen-7B-Python-4bit", device_map="auto")A finetuned model trained on 5 datasets with a total of 875928 rows. This model was an experiment, as I wanted to train a model with a lot of python code and see the results.
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Vo1dAbyss/DeepSeek-R1-Distill-Qwen-7B-Python-4bit", device_map="auto")