Quantizations of https://huggingface.co/deepseek-ai/m-a-p/OpenCodeInterpreter-DS-6.7B

From original readme

Model Usage

Inference

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_path="m-a-p/OpenCodeInterpreter-DS-6.7B"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

prompt = "Write a function to find the shared elements from the given two lists."
inputs = tokenizer.apply_chat_template(
        [{'role': 'user', 'content': prompt }],
        return_tensors="pt"
    ).to(model.device)
outputs = model.generate(
    inputs, 
    max_new_tokens=1024,
    do_sample=False,
    pad_token_id=tokenizer.eos_token_id,
    eos_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))