Arxiv:2501.12948 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Conversational Ja Japanese Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/cyberagent/DeepSeek-R1-Distill-Qwen-14B-Japanese
DeepSeek R1 Distill Qwen 14B Japanese 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 14B Japanese Parameters and Internals
| LLM Name | DeepSeek R1 Distill Qwen 14B Japanese |
| Repository 🤗 | https://huggingface.co/cyberagent/DeepSeek-R1-Distill-Qwen-14B-Japanese |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 29.7 GB |
| Updated | 2025-05-15 |
| Maintainer | cyberagent |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | ja |
| Model Architecture | Qwen2ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to DeepSeek R1 Distill Qwen 14B Japanese
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 14B Instruct 1M | 986K / 29.6 GB | 162428 | 306 |
| T3Q Qwen2.5 14B V1.0 E3 | 986K / 29.7 GB | 864 | 25 |
| ZYH LLM Qwen2.5 14B V4 | 986K / 29.7 GB | 146 | 6 |
| Qwen2.5 14B 1M YOYO V3 | 986K / 29.7 GB | 254 | 4 |
| ZYH LLM Qwen2.5 14B V3 | 986K / 29.7 GB | 198 | 8 |
| Impish QWEN 14B 1M | 986K / 29.7 GB | 228 | 16 |
| Qwen2.5 14B YOYO Latest V2 | 986K / 29.7 GB | 129 | 0 |
| Qwen2.5 14B YOYO V4 | 986K / 29.7 GB | 11 | 4 |
| ...14B Instruct 1M GRPO Reasoning | 986K / 29.7 GB | 26 | 4 |
| Etr1o V1.2 | 986K / 29.7 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than cyberagent/DeepSeek-R1-Distill-Qwen-14B-Japanese .
Rank the DeepSeek R1 Distill Qwen 14B Japanese 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