ThomasBaruzier/Qwen2.5-Coder-0.5B-Instruct-GGUF

Llama.cpp imatrix quantizations of Qwen/Qwen2.5-Coder-0.5B-Instruct

Using llama.cpp commit 3ad5451 for quantization.

All quants were made using the imatrix option and Bartowski's calibration file.

---

Perplexity table (the lower the better)

Quant	Size (MB)	PPL	Size (%)	Accuracy (%)	PPL error rate
IQ1_S	301	32.6390	31.75	69.27	0.59
IQ1_M	303	29.9721	31.96	75.43	0.53
IQ2_XXS	306	28.2728	32.28	79.97	0.52
IQ2_XS	309	26.5764	32.59	85.07	0.48
IQ2_S	310	26.3276	32.70	85.88	0.48
IQ2_M	313	25.6364	33.02	88.19	0.46
Q2_K_S	315	25.6897	33.23	88.01	0.46
IQ3_XXS	318	24.6070	33.54	91.88	0.44
Q3_K_S	322	24.5354	33.97	92.15	0.44
IQ3_S	322	24.0335	33.97	94.07	0.43
IQ3_XS	322	24.0335	33.97	94.07	0.43
Q2_K	322	24.4565	33.97	92.45	0.44
IQ3_M	326	23.8652	34.39	94.74	0.43
IQ4_XS	333	23.6261	35.13	95.70	0.42
IQ4_NL	336	23.6102	35.44	95.76	0.42
Q4_0	336	23.8547	35.44	94.78	0.42
Q3_K_M	338	23.5268	35.65	96.10	0.42
Q3_K_L	352	23.3214	37.13	96.95	0.42
Q4_1	357	23.3396	37.66	96.87	0.42
Q4_K_S	367	23.2008	38.71	97.45	0.41
Q5_0	379	23.1914	39.98	97.49	0.41
Q4_K_M	379	23.1306	39.98	97.75	0.41
Q5_K_S	393	22.8146	41.46	99.10	0.41
Q5_1	399	22.8381	42.09	99.00	0.41
Q5_K_M	400	22.7761	42.19	99.27	0.41
Q6_K	482	22.6302	50.84	99.91	0.40
Q8_0	506	22.6359	53.38	99.88	0.40
F16	948	22.6094	100	100	0.40

---

Qwen2.5-Coder-0.5B-Instruct

Introduction

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

• Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.
• A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.

This repo contains the instruction-tuned 0.5B Qwen2.5-Coder model, which has the following features:

• Type: Causal Language Models
• Training Stage: Pretraining & Post-training
• Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
• Number of Parameters: 0.49B
• Number of Paramaters (Non-Embedding): 0.36B
• Number of Layers: 24
• Number of Attention Heads (GQA): 14 for Q and 2 for KV
• Context Length: Full 32,768 tokens

For more details, please refer to our blog, GitHub, Documentation, Arxiv.

Requirements

The code of Qwen2.5-Coder has been in the latest Hugging face transformers and we advise you to use the latest version of transformers.

With transformers<4.37.0, you will encounter the following error:

KeyError: 'qwen2'

Quickstart

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen2.5-Coder-0.5B-Instruct"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "write a quick sort algorithm."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Evaluation & Performance

Detailed evaluation results are reported in this 📑 blog.

For requirements on GPU memory and the respective throughput, see results here.

Citation

If you find our work helpful, feel free to give us a cite.

@article{hui2024qwen2,
      title={Qwen2. 5-Coder Technical Report},
      author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
      journal={arXiv preprint arXiv:2409.12186},
      year={2024}
}
@article{qwen2,
      title={Qwen2 Technical Report}, 
      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
      journal={arXiv preprint arXiv:2407.10671},
      year={2024}
}