README.md

metadata

language:
  - en
  - id
tags:
  - qwen
  - code
  - merged
  - optimized
pipeline_tag: text-generation
license: apache-2.0

{full_repo_name} Merged (Optimized)

This is an optimized merged version of the fine-tuned Qwen2.5 Coder model. It combines:

• Base model: {base_model_name}
• Fine-tuned adapter: {adapter_path}

The model has been optimized using float16 precision and efficient serialization.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "{full_repo_name}",
    trust_remote_code=True,
    torch_dtype=torch.float16  # Use float16 for efficiency
)
tokenizer = AutoTokenizer.from_pretrained("{full_repo_name}", trust_remote_code=True)