Model Card on HF 🤗: https://huggingface.co/sumink/Qwensci
Qwensci Benchmarks
MMLU Pro: 2.89
GPQA: 1.12
MUSR: 3.61
BBH: 6.32
IFEval: 17.4 vs 88 (so35)-80.2%
MATH Lvl 5: 2.04
LLME Score: 0.23661
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)
Qwensci Parameters and Internals
| LLM Name | Qwensci |
| Repository 🤗 | https://huggingface.co/sumink/Qwensci |
| Model Size | 1.5b |
| Required VRAM | 6.2 GB |
| Updated | 2025-04-10 |
| Maintainer | sumink |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 151666 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to Qwensci
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReaderLM V2 | 500K / 3.1 GB | 64774 | 635 |
| Reader Lm 1.5B | 250K / 3.1 GB | 693 | 597 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 1815675 | 1188 |
| DeepScaleR 1.5B Preview | 128K / 7.1 GB | 83977 | 552 |
| Qwen2.5 1.5B | 128K / 3.1 GB | 607775 | 102 |
| DeepCoder 1.5B Preview | 128K / 7.1 GB | 3112 | 63 |
| OpenMath Nemotron 1.5B | 128K / 3.1 GB | 2936 | 19 |
| ZR1 1.5B | 128K / 7.1 GB | 1367 | 63 |
| AceInstruct 1.5B | 128K / 3.5 GB | 4138 | 20 |
| Qwen2 1.5B | 128K / 3.1 GB | 180577 | 92 |
Note: green Score (e.g. "73.2") means that the model is better than sumink/Qwensci .
Rank the Qwensci 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? 47368 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227