Arxiv:2402.03300 Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Conversational Dataset:jhn9803/hendrycks-math... Endpoints compatible Generated from trainer Grpo Open-r1 Qwen2 Region:us Safetensors Trl
Model Card on HF 🤗: https://huggingface.co/jhn9803/DeepSeek-R1-Distill-Qwen-1.5B-MATH345-VLOO-EP5-LR1e06
DeepSeek R1 Distill Qwen 1.5B MATH345 VLOO EP5 LR1e06 Benchmarks
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)
DeepSeek R1 Distill Qwen 1.5B MATH345 VLOO EP5 LR1e06 Parameters and Internals
| LLM Name | DeepSeek R1 Distill Qwen 1.5B MATH345 VLOO EP5 LR1e06 |
| Repository 🤗 | https://huggingface.co/jhn9803/DeepSeek-R1-Distill-Qwen-1.5B-MATH345-VLOO-EP5-LR1e06 |
| Model Name | DeepSeek-R1-Distill-Qwen-1.5B-MATH345-VLOO-EP5-LR1e06 |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 3.5 GB |
| Updated | 2025-07-29 |
| Maintainer | jhn9803 |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.52.3 |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives to DeepSeek R1 Distill Qwen 1.5B MATH345 VLOO EP5 LR1e06
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReaderLM V2 | 500K / 3.1 GB | 13608 | 677 |
| Reader Lm 1.5B | 250K / 3.1 GB | 1081 | 601 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 977679 | 1280 |
| OpenReasoning Nemotron 1.5B | 128K / 3.1 GB | 3453 | 30 |
| ...n Research Reasoning Qwen 1.5B | 128K / 3.5 GB | 10438 | 180 |
| DeepScaleR 1.5B Preview | 128K / 7.1 GB | 48959 | 568 |
| Qwen2.5 1.5B | 128K / 3.1 GB | 418802 | 110 |
| AceInstruct 1.5B | 128K / 3.5 GB | 24279 | 20 |
| Qwen2 1.5B | 128K / 3.1 GB | 125293 | 94 |
| Stella En 1.5B V5 | 128K / 6.2 GB | 581890 | 211 |
Note: green Score (e.g. "73.2") means that the model is better than jhn9803/DeepSeek-R1-Distill-Qwen-1.5B-MATH345-VLOO-EP5-LR1e06 .
Rank the DeepSeek R1 Distill Qwen 1.5B MATH345 VLOO EP5 LR1e06 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? 50200 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124