DeepSeek-R1-Distill-Qwen-32B

hengwen/DeepSeek-R1-Distill-Qwen-32B

DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. Please use our setting to run these models.

123.7K Pulls 2 Tags Updated 11 months ago

aia/DeepSeek-R1-Distill-Qwen-32B-Uncensored-i1

2,359 Pulls 1 Tag Updated 10 months ago

jerry0012000/DeepSeek-R1-Distill-Qwen-32B-Q4_K_M

513 Pulls 1 Tag Updated 10 months ago

wao/DeepSeek-R1-Distill-Qwen-32B-Japanese

Japanese instruction-tuned LLM by CyberAgent, distilled from Qwen-72B.

182 Pulls 1 Tag Updated 7 months ago

bsahane/DeepSeek-R1-Distill-Qwen-32B

113 Pulls 1 Tag Updated 10 months ago

hellonico/DeepSeek-R1-Distill-Qwen-32B-Japanese

68 Pulls 1 Tag Updated 10 months ago

xitao/DeepSeek-R1-Distill-Qwen-32B-QMind

20 Pulls 2 Tags Updated 10 months ago

huihui_ai/deepseek-r1-Fusion

DeepSeek-R1-Distill-Qwen-Coder-32B-Fusion-9010 is a mixed model that combines the strengths of two powerful DeepSeek-R1-Distill-Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.

32b

1,075 Pulls 6 Tags Updated 9 months ago