Arxiv:2502.01718 Acecoder Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-... Code Codegen Dataset:tiger-lab/acecode-87k En Instruct Qwen Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Ins-Rule
AceCoder Qwen2.5 Coder 7B Ins Rule Benchmarks
MMLU Pro: 26.98
GPQA: 3.69
MUSR: 8.71
BBH: 30.54
IFEval: 62.22 vs 88 (so35)-29.3%
MATH Lvl 5: 36.03
LLME Score: 0.33405
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
AceCoder Qwen2.5 Coder 7B Ins Rule Parameters and Internals
| LLM Name | AceCoder Qwen2.5 Coder 7B Ins Rule |
| Repository 🤗 | https://huggingface.co/TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Ins-Rule |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 59 GB |
| Updated | 2025-03-12 |
| Maintainer | TIGER-Lab |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Generates Code | Yes |
| Model Architecture | Qwen2ForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to AceCoder Qwen2.5 Coder 7B Ins Rule
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| StockQwen 2.5 7B | 128K / 15.2 GB | 24 | 3 |
| Qwen2.5 Coder 7B Instruct | 32K / 15.2 GB | 156498 | 436 |
| Viper Coder HybridMini V1.3 | 32K / 15.2 GB | 955 | 15 |
| Qwen2.5 7B MS Destroyer | 32K / 15.2 GB | 78 | 1 |
| Qwen2.5 MFANN 7B SLERP V1.2 | 32K / 14.8 GB | 42 | 0 |
| Qwen2.5 MFANN 7B SLERPv1.1 | 32K / 15.2 GB | 53 | 0 |
| ...erated MFANN Slerp Unretrained | 32K / 15.2 GB | 49 | 1 |
| Qwen2.5 7B MFANN Slerp | 32K / 15.2 GB | 20 | 1 |
| ...r Scholar 7B Abliterated MFANN | 32K / 30.5 GB | 24 | 2 |
| Rombos Coder V2.5 Qwen 7B | 32K / 15.2 GB | 144 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Ins-Rule .
Rank the AceCoder Qwen2.5 Coder 7B Ins Rule Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 44902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227