Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Conversational Dataset:ai-mo/numinamath-cot Dataset:amphora/qwq-longcot-13... Dataset:novasky-ai/sky-t1 data... Dataset:prithivmlmods/deepthin... Dataset:prithivmlmods/math-sol... Deepseek Distill En Endpoints compatible Qwen2 Qwen2.5 Qwq R1 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/prithivMLmods/QwQ-R1-Distill-1.5B-CoT
QwQ R1 Distill 1.5B CoT Benchmarks
MMLU Pro: 10.15
GPQA: 4.81
MUSR: 1.76
BBH: 11.48
IFEval: 21.94 vs 88 (so35)-75.1%
MATH Lvl 5: 24.62
LLME Score: 0.33496
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 R1 Distill 1.5B CoT Parameters and Internals
| LLM Name | QwQ R1 Distill 1.5B CoT |
| Repository 🤗 | https://huggingface.co/prithivMLmods/QwQ-R1-Distill-1.5B-CoT |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 3.5 GB |
| Updated | 2025-02-05 |
| Maintainer | prithivMLmods |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives to QwQ R1 Distill 1.5B CoT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReaderLM V2 | 500K / 3.5 GB | 23287 | 473 |
| Reader Lm 1.5B | 250K / 3.1 GB | 8819 | 584 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 386547 | 659 |
| ...Seek R1 Distill Qwen 1.5B ONNX | 128K / GB | 39223 | 37 |
| Qwen2.5 1.5B | 128K / 3.1 GB | 370941 | 61 |
| ...ek R1 ReDistill Qwen 1.5B V1.0 | 128K / 3.6 GB | 307 | 42 |
| Stella En 1.5B V5 | 128K / 6.2 GB | 581890 | 211 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 4858 | 6 |
| AceInstruct 1.5B | 128K / 3.5 GB | 374 | 10 |
| Bellatrix 1.5B XElite | 128K / 3.5 GB | 221 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than prithivMLmods/QwQ-R1-Distill-1.5B-CoT .
Rank the QwQ R1 Distill 1.5B CoT 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227