Arxiv:2412.15084 Aceinstruct Code Conversational En General domain Instruct Instruct model Math Nvidia Pytorch Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/nvidia/AceInstruct-1.5B
AceInstruct 1.5B Benchmarks
MMLU Pro: 17.49
GPQA: 2.91
MUSR: 2.08
BBH: 15.47
IFEval: 39.48 vs 88 (so35)-55.1%
MATH Lvl 5: 31.27
LLME Score: 0.33242
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)
AceInstruct 1.5B Parameters and Internals
| LLM Name | AceInstruct 1.5B |
| Repository 🤗 | https://huggingface.co/nvidia/AceInstruct-1.5B |
| Model Size | 1.5b |
| Required VRAM | 3.5 GB |
| Updated | 2025-07-25 |
| Maintainer | nvidia |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to AceInstruct 1.5B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| OpenReasoning Nemotron 1.5B | 128K / 3.1 GB | 3093 | 28 |
| Gte Qwen2 1.5B Instruct | 128K / 7.1 GB | 124333 | 223 |
| ... Abliterated TIES Qwen2.5 1.5B | 128K / 3.5 GB | 7 | 0 |
| WiroAI Finance Qwen 1.5B | 128K / 3.5 GB | 1785 | 19 |
| Saba1 1.8B | 128K / 3.6 GB | 5 | 1 |
| Bellatrix 1.5B XElite | 128K / 3.5 GB | 3 | 3 |
| Miniclaus Qw1.5B UNAMGS | 128K / 3.5 GB | 10 | 8 |
| GCIRS Reasoning 1.5B R1 | 128K / 3.5 GB | 7 | 1 |
| ...illed Scout 1.5B Instruct Gen1 | 128K / 3.5 GB | 5 | 0 |
| Deepthink 1.5B Open PRM | 128K / 7.1 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than nvidia/AceInstruct-1.5B .
Rank the AceInstruct 1.5B 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? 50068 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124