Autotrain compatible Base model:finetune:nvidia/ace... Base model:nvidia/acemath-1.5b... Conversational En Endpoints compatible Grpo Instruct Lora Pytorch Qwen2 Region:us Safetensors Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/NikolaSigmoid/acemath-200
Acemath 200 Benchmarks
MMLU Pro: 15.29
GPQA: 3.69
MUSR: 7.23
BBH: 19.83
IFEval: 28.49 vs 88 (so35)-67.6%
MATH Lvl 5: 30.51
LLME Score: 0.25931
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)
Acemath 200 Parameters and Internals
| LLM Name | Acemath 200 |
| Repository 🤗 | https://huggingface.co/NikolaSigmoid/acemath-200 |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 0.1 GB |
| Updated | 2025-09-23 |
| Maintainer | NikolaSigmoid |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|up_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
| Errors | replace |
Best Alternatives to Acemath 200
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AceMath 1.5B Instruct 1epoch | 0K / 0.1 GB | 16 | 0 |
| Qwen First Aid Medium | 0K / 1.9 GB | 0 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than NikolaSigmoid/acemath-200 .
Rank the Acemath 200 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124