README.md

metadata

base_model:
  - Qwen/Qwen2.5-Coder-0.5B-Instruct
tags:
  - merge
  - mergekit
  - lazymergekit
  - Qwen/Qwen2.5-Coder-0.5B-Instruct

qwen-CoMa-0.5b

qwen-CoMa-0.5b is a merge of the following models using LazyMergekit:

• Qwen/Qwen2.5-Coder-0.5B-Instruct
• Youlln/ECE.EIFFEIL.ia-0.5B-SLERP as base.

Uses

This model was made for improved math and coding capabilities.

🧩 Configuration

models:
  - model: Youlln/ECE.EIFFEIL.ia-0.5B-SLERP
    #no parameters necessary for base model
  - model: Qwen/Qwen2.5-Coder-0.5B-Instruct
    parameters:
      density: 0.5
      weight: 0.5


merge_method: ties
base_model: Youlln/ECE.EIFFEIL.ia-0.5B-SLERP
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "someon98/qwen-CoMa-0.5b"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])