Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins... Conversational Dataset:opengpt-x/gsm8kx De Endpoints compatible Instruct Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/malteos/german-r1
German R1 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)
German R1 Parameters and Internals
| LLM Name | German R1 |
| Repository 🤗 | https://huggingface.co/malteos/german-r1 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2025-02-22 |
| Maintainer | malteos |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | de |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.48.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to German R1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba2 3B | 128K / 6.2 GB | 56 | 0 |
| SmallThinker 3B Preview | 32K / 6.8 GB | 109315 | 386 |
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 595245 | 191 |
| Calme 3.2 Baguette 3B | 32K / 11 GB | 2898 | 1 |
| Calme 3.1 Baguette 3B | 32K / 6.2 GB | 3105 | 1 |
| Calme 3.2 Instruct 3B | 32K / 11 GB | 3030 | 3 |
| Calme 3.1 Instruct 3B | 32K / 11 GB | 3035 | 3 |
| Calme 3.3 Instruct 3B | 32K / 11 GB | 709 | 3 |
| Qwen2.5 3B RP Thinker V2 | 32K / 6.8 GB | 70 | 1 |
| Qwen2.5 3B Model Stock | 32K / 6.8 GB | 18 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than malteos/german-r1 .
Rank the German R1 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227