Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-0.5b-i... Conversational Dataset:amphora/qwq-longcot-13... Dataset:powerinfer/longcot-ref... Dataset:powerinfer/qwq-longcot... En Endpoints compatible Instruct Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/kz919/QwQ-0.5B-Distilled-SFT
QwQ 0.5B Distilled SFT Benchmarks
MMLU Pro: 6.53
GPQA: 1.45
MUSR: 1.11
BBH: 7.28
IFEval: 30.77 vs 88 (so35)-65%
MATH Lvl 5: 7.4
LLME Score: 0.2911
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)
QwQ 0.5B Distilled SFT Parameters and Internals
| LLM Name | QwQ 0.5B Distilled SFT |
| Repository 🤗 | https://huggingface.co/kz919/QwQ-0.5B-Distilled-SFT |
| Base Model(s) | |
| Model Size | 0.5b |
| Required VRAM | 1 GB |
| Updated | 2025-03-22 |
| Maintainer | kz919 |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to QwQ 0.5B Distilled SFT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 0.5B Abyme Merge3 | 128K / 1.3 GB | 30 | 1 |
| Qwen2 0.5B Abyme Merge2 | 128K / 0.3 GB | 14 | 0 |
| Qwen2.5 0.5B Instruct | 32K / 1 GB | 998680 | 273 |
| Qwen2 0.5B Instruct | 32K / 1 GB | 351485 | 180 |
| Qwen2.5 Coder 0.5B Instruct | 32K / 1 GB | 49626 | 42 |
| Qwen2.5 0.5B Portuguese V1 | 32K / 1 GB | 2459 | 4 |
| QwQ 0.5B | 32K / 1 GB | 663 | 3 |
| Lb Reranker 0.5B V1.0 | 32K / 1 GB | 1651 | 63 |
| FastThink 0.5B Tiny | 32K / 1 GB | 1268 | 4 |
| Hammer2.1 0.5B | 32K / 1 GB | 7671 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than kz919/QwQ-0.5B-Distilled-SFT .
Rank the QwQ 0.5B Distilled SFT 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? 45389 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227