Total runs:
100.8K
Run Growth:
61.8K
Growth Rate:
61.30%
Sponsored by
Tripo AI
TIGER-Lab / AceCoder-Qwen2.5-Coder-7B-Ins-Rule
Model's Last Updated: February 13 2025
Introduction of AceCoder-Qwen2.5-Coder-7B-Ins-Rule
Model Details of AceCoder-Qwen2.5-Coder-7B-Ins-Rule
🂡 AceCode-89K
Paper | Github | AceCode-89K | AceCodePair-300K | RM/RL Models
We introduce AceCoder, the first work to propose a fully automated pipeline for synthesizing large-scale reliable tests used for the reward model training and reinforcement learning in the coding scenario. To do this, we curated the dataset AceCode-89K, where we start from a seed code dataset and prompt powerful LLMs to "imagine" proper test cases for the coding question and filter the noisy ones. We sample inferences from existing coder models and compute their pass rate as the reliable and verifiable rewards for both training the reward model and conducting the reinforcement learning for coder LLM.
Note
- This model is trained on the hard version of TIGER-Lab/AceCode-89K with about 22k examples, using the binary pass rate (rule based reward) as the reward
- You can reproduce the hard version of TIGER-Lab/AceCode-89K using script in our Github
- The training takes 6 hours to finish on 8 x H100 GPUs in around 80 optimization steps.
- To reproduce the training, please refer to our training script in the Github
- To use the model, please refer to the codes in Qwen/Qwen2.5-7B-Instruct
- Training wandb link
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Ins-Rule"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Give me a short introduction to large language model."
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]
Performance
Citation
@article{AceCoder,
title={AceCoder: Acing Coder RL via Automated Test-Case Synthesis},
author={Zeng, Huaye and Jiang, Dongfu and Wang, Haozhe and Nie, Ping and Chen, Xiaotong and Chen, Wenhu},
journal={ArXiv},
year={2025},
volume={abs/2207.01780}
}
Runs of TIGER-Lab AceCoder-Qwen2.5-Coder-7B-Ins-Rule on huggingface.co
109
Total runs
59
24-hour runs
60
3-day runs
84
7-day runs
94
30-day runs
More Information About AceCoder-Qwen2.5-Coder-7B-Ins-Rule huggingface.co Model
Url of AceCoder-Qwen2.5-Coder-7B-Ins-Rule
AceCoder-Qwen2.5-Coder-7B-Ins-Rule huggingface.co Url
Provider of AceCoder-Qwen2.5-Coder-7B-Ins-Rule huggingface.co
Other API from TIGER-Lab
Updated:November 15 2024
Total runs:
12.3K
Run Growth:
594
Growth Rate:
4.84%
Total runs:
10.6K
Run Growth:
-3.6K
Growth Rate:
-34.41%
Total runs:
8.3K
Run Growth:
323
Growth Rate:
3.90%
Total runs:
3.2K
Run Growth:
2.7K
Growth Rate:
84.03%
Total runs:
2.7K
Run Growth:
2.6K
Growth Rate:
96.59%
Total runs:
1.4K
Run Growth:
120
Growth Rate:
8.64%
Total runs:
923
Run Growth:
-10.3K
Growth Rate:
-1116.36%
Total runs:
694
Run Growth:
0
Growth Rate:
0.00%
Total runs:
579
Run Growth:
-2.3K
Growth Rate:
-389.98%
Total runs:
498
Run Growth:
110
Growth Rate:
22.09%
Total runs:
394
Run Growth:
308
Growth Rate:
78.17%
Total runs:
262
Run Growth:
155
Growth Rate:
59.16%
Total runs:
228
Run Growth:
99
Growth Rate:
43.42%
Total runs:
165
Run Growth:
128
Growth Rate:
77.58%
Total runs:
156
Run Growth:
19
Growth Rate:
12.18%
Total runs:
156
Run Growth:
134
Growth Rate:
85.90%
Total runs:
153
Run Growth:
110
Growth Rate:
71.90%
Total runs:
151
Run Growth:
129
Growth Rate:
85.43%
Total runs:
139
Run Growth:
18
Growth Rate:
12.95%
Total runs:
138
Run Growth:
66
Growth Rate:
47.83%
Total runs:
91
Run Growth:
29
Growth Rate:
31.87%
Total runs:
83
Run Growth:
-23
Growth Rate:
-28.40%
Total runs:
54
Run Growth:
50
Growth Rate:
92.59%
Total runs:
46
Run Growth:
28
Growth Rate:
60.87%
Total runs:
46
Run Growth:
-327
Growth Rate:
-710.87%
Total runs:
38
Run Growth:
-31
Growth Rate:
-81.58%
Total runs:
32
Run Growth:
-425
Growth Rate:
-1370.97%
Total runs:
26
Run Growth:
13
Growth Rate:
50.00%
Total runs:
24
Run Growth:
3
Growth Rate:
12.50%
Total runs:
23
Run Growth:
2
Growth Rate:
8.70%
Total runs:
21
Run Growth:
-69
Growth Rate:
-328.57%
Total runs:
21
Run Growth:
3
Growth Rate:
14.29%
Total runs:
18
Run Growth:
-3
Growth Rate:
-20.00%
Total runs:
17
Run Growth:
0
Growth Rate:
0.00%
Total runs:
15
Run Growth:
5
Growth Rate:
38.46%
Total runs:
14
Run Growth:
3
Growth Rate:
21.43%
Total runs:
14
Run Growth:
6
Growth Rate:
42.86%
Total runs:
13
Run Growth:
0
Growth Rate:
0.00%
Total runs:
13
Run Growth:
3
Growth Rate:
23.08%
Total runs:
11
Run Growth:
3
Growth Rate:
27.27%
Total runs:
11
Run Growth:
-6
Growth Rate:
-54.55%
Total runs:
10
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9
Run Growth:
-12
Growth Rate:
-133.33%
Total runs:
7
Run Growth:
0
Growth Rate:
0.00%
Total runs:
7
Run Growth:
-5
Growth Rate:
-71.43%
Total runs:
6
Run Growth:
-10
Growth Rate:
-166.67%
Total runs:
6
Run Growth:
-3
Growth Rate:
-42.86%
Total runs:
6
Run Growth:
1
Growth Rate:
16.67%
Total runs:
5
Run Growth:
-40
Growth Rate:
-800.00%
Total runs:
5
Run Growth:
-8
Growth Rate:
-160.00%
Total runs:
5
Run Growth:
-23
Growth Rate:
-460.00%
Total runs:
4
Run Growth:
-1
Growth Rate:
-25.00%
Total runs:
3
Run Growth:
2
Growth Rate:
66.67%