datapaf/DeepSeekCoderCodeQnA

Model Card for DeepSeekCodeCodeQ&A

This is a version of DeepSeek-Coder model that was fine-tuned on the grammatically corrected texts.

Model Details

Model Description

• Model type: LLaMa
• Number of Parameters: 6.7B
• Supported Programming Language: Python
• Finetuned from model: DeepSeek-Coder

Model Sources [optional]

• Repository: GitHub Repo
• Paper: "Leveraging Large Language Models in Code Question Answering: Baselines and Issues" Georgy Andryushchenko, Vladimir V. Ivanov, Vladimir Makharev, Elizaveta Tukhtina, Aidar Valeev

How to Get Started with the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('deepseek-ai/deepseek-coder-6.7b-instruct')
model = AutoModelForCausalLM.from_pretrained('datapaf/DeepSeekCoderCodeQnA', device_map="cuda")

code = ... # Your Python code snippet here
question = ... # Your question regarding the snippet here

q = f"{question}\n{code}"

inputs = tokenizer.encode(q, return_tensors="pt").to('cuda')
outputs = model.generate(inputs, max_new_tokens=512, pad_token_id=tokenizer.eos_token_id)
text = tokenizer.decode(outputs[0])
print(text)

-->