DeepSeek R1 Distill Qwen 32B Japanese by cyberagent

 »  All LLMs  »  cyberagent  »  DeepSeek R1 Distill Qwen 32B Japanese   URL Share it on

  Arxiv:2501.12948 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Ja   Japanese   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

DeepSeek R1 Distill Qwen 32B Japanese Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

DeepSeek R1 Distill Qwen 32B Japanese Parameters and Internals

LLM NameDeepSeek R1 Distill Qwen 32B Japanese
Repository 🤗https://huggingface.co/cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese 
Base Model(s)  DeepSeek R1 Distill Qwen 32B   deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Model Size32b
Required VRAM65.8 GB
Updated2025-06-11
Maintainercyberagent
Model Typeqwen2
Model Files  4.9 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   2.1 GB: 14-of-14
Supported Languagesja
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.47.0
Tokenizer ClassLlamaTokenizer
Padding Token<|end▁of▁sentence|>
Vocabulary Size152064
Torch Data Typebfloat16
DeepSeek R1 Distill Qwen 32B Japanese (cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese)

Quantized Models of the DeepSeek R1 Distill Qwen 32B Japanese

Model
Likes
Downloads
VRAM
...Distill Qwen 32B Japanese 4bit27618 GB
...Distill Qwen 32B Japanese 8bit26834 GB

Best Alternatives to DeepSeek R1 Distill Qwen 32B Japanese

Best Alternatives
Context / RAM
Downloads
Likes
Openbuddy Qwq 32B V24.2 200K195K / 65.8 GB153
Openbuddy Qwq 32B V24.1 200K195K / 65.8 GB133
Openbuddy Qwq 32B V25.2q 200K195K / 65.8 GB103
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB152
DeepSeek R1 Distill Qwen 32B128K / 65.7 GB2419101390
QwenLong L1 32B128K / 65.6 GB3376149
Qwen2.5 32B128K / 65.5 GB103744152
FairyR1 32B128K / 65.8 GB190398
RomboUltima 32B128K / 20.7 GB8564
Cogito V1 Preview Qwen 32B128K / 65.7 GB19255109
Note: green Score (e.g. "73.2") means that the model is better than cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese.

Rank the DeepSeek R1 Distill Qwen 32B 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 48079 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124