Merged Model Autotrain compatible Base model:qwen/qwen2.5-1.5b Base model:sumink/qwenftmodel Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/sumink/Qmerft
Qmerft Benchmarks
MMLU Pro: 1.74
GPQA: 0.34
MUSR: 3.93
BBH: 1.95
IFEval: 15.64 vs 88 (so35)-82.2%
MATH Lvl 5: 0.23
LLME Score: 0.23466
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)
Qmerft Parameters and Internals
| LLM Name | Qmerft |
| Repository 🤗 | https://huggingface.co/sumink/Qmerft |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 1.5b |
| Required VRAM | 3.5 GB |
| Updated | 2025-05-21 |
| Maintainer | sumink |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qmerft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReaderLM V2 | 500K / 3.1 GB | 61035 | 637 |
| Reader Lm 1.5B | 250K / 3.1 GB | 567 | 597 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 1441410 | 1194 |
| DeepScaleR 1.5B Preview | 128K / 7.1 GB | 64836 | 553 |
| Qwen2.5 1.5B | 128K / 3.1 GB | 496176 | 102 |
| DeepCoder 1.5B Preview | 128K / 7.1 GB | 2125 | 64 |
| OpenMath Nemotron 1.5B | 128K / 3.1 GB | 3328 | 19 |
| AceInstruct 1.5B | 128K / 3.5 GB | 4280 | 20 |
| ZR1 1.5B | 128K / 7.1 GB | 717 | 64 |
| Qwen2 1.5B | 128K / 3.1 GB | 124801 | 92 |
Note: green Score (e.g. "73.2") means that the model is better than sumink/Qmerft .
Rank the Qmerft 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? 47473 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227