Files changed (1) hide show
  1. README.md +112 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - Qwen/Qwen2.5-Coder-1.5B
7
+ pipeline_tag: text-generation
8
+ library_name: transformers
9
+ tags:
10
+ - code
11
+ - codeqwen
12
+ - chat
13
+ - qwen
14
+ - qwen-coder
15
+ ---
16
+
17
+
18
+ # Qwen2.5-Coder-1.5B-Instruct
19
+
20
+ ## Introduction
21
+
22
+ Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). For Qwen2.5-Coder, we release three base language models and instruction-tuned language models, 1.5, 7 and 32 (coming soon) billion parameters. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:
23
+
24
+ - 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.
25
+ - 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.
26
+ - **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
27
+
28
+ **This repo contains the 1.5B Qwen2.5-Coder model**, which has the following features:
29
+ - Type: Causal Language Models
30
+ - Training Stage: Pretraining & Post-training
31
+ - Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
32
+ - Number of Parameters: 1.54B
33
+ - Number of Paramaters (Non-Embedding): 1.31B
34
+ - Number of Layers: 28
35
+ - Number of Attention Heads (GQA): 12 for Q and 2 for KV
36
+ - Context Length: Full 32,768 tokens and generation 8192 tokens
37
+
38
+ For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), and [Documentation](https://qwen.readthedocs.io/en/latest/).
39
+
40
+ ## Requirements
41
+
42
+ 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`.
43
+
44
+ With `transformers<4.37.0`, you will encounter the following error:
45
+ ```
46
+ KeyError: 'qwen2'
47
+ ```
48
+
49
+ ## Quickstart
50
+
51
+ Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
52
+
53
+ ```python
54
+ from transformers import AutoModelForCausalLM, AutoTokenizer
55
+
56
+ model_name = "Qwen/Qwen2.5-Coder-1.5B-Instruct"
57
+
58
+ model = AutoModelForCausalLM.from_pretrained(
59
+ model_name,
60
+ torch_dtype="auto",
61
+ device_map="auto"
62
+ )
63
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
64
+
65
+ prompt = "write a quick sort algorithm."
66
+ messages = [
67
+ {"role": "system", "content": "You are a helpful assistant."},
68
+ {"role": "user", "content": prompt}
69
+ ]
70
+ text = tokenizer.apply_chat_template(
71
+ messages,
72
+ tokenize=False,
73
+ add_generation_prompt=True
74
+ )
75
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
76
+
77
+ generated_ids = model.generate(
78
+ **model_inputs,
79
+ max_new_tokens=512
80
+ )
81
+ generated_ids = [
82
+ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
83
+ ]
84
+
85
+ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
86
+ ```
87
+
88
+ ## Evaluation & Performance
89
+
90
+ Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-coder/).
91
+
92
+ For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
93
+
94
+ ## Citation
95
+
96
+ If you find our work helpful, feel free to give us a cite.
97
+
98
+ ```
99
+ @misc{qwen2.5,
100
+ title = {Qwen2.5: A Party of Foundation Models},
101
+ url = {https://qwenlm.github.io/blog/qwen2.5/},
102
+ author = {Qwen Team},
103
+ month = {September},
104
+ year = {2024}
105
+ }
106
+ @article{qwen2,
107
+ title={Qwen2 Technical Report},
108
+ 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},
109
+ journal={arXiv preprint arXiv:2407.10671},
110
+ year={2024}
111
+ }
112
+ ```