Models

Warm

llama31-8b-16k

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

755

1,342,473

D
Warm

qwen3-8b

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

804

455,040

D
Warm

qwen25-7b-lc

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

663

419,408

D
Warm

deepseek-v3-lc

deepseek-ai/DeepSeek-V3-0324

2,980

404,914

D
Warm

qwen25-32b-lc

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

1,403

323,076

D
Warm

qwen25-14b-lc

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

529

321,239

D
Warm

llama33-70b-16k

deepseek-ai/DeepSeek-R1-Distill-Llama-70B

695

272,495

D
Warm

deepseek-v3-lc

deepseek-ai/DeepSeek-R1-0528

2,120

154,886

D
Warm

llama31-8b-16k

RLHFlow/Llama3.1-8B-PRM-Deepseek-Data

32

26,447

R
Warm

qwen2-7b-lc

fangyili/deepseek-distill-qwen-7b-merged-peft

0

15,262

F
Warm

llama31-8b-16k

unsloth/DeepSeek-R1-Distill-Llama-8B

96

14,567

U
Warm

qwen2-7b-lc

unsloth/DeepSeek-R1-Distill-Qwen-7B

12

11,087

U
Warm

qwen2-32b-lc

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

11

9,931

U
Warm

qwen2-14b-lc

cyberagent/DeepSeek-R1-Distill-Qwen-14B-Japanese

83

7,155

C
Warm

qwen25-32b-lc

rinna/deepseek-r1-distill-qwen2.5-bakeneko-32b

7

6,710

R
Warm

qwen2-14b-lc

unsloth/DeepSeek-R1-Distill-Qwen-14B

16

5,889

U
Warm

llama31-8b-16k

UNIVA-Bllossom/DeepSeek-llama3.1-Bllossom-8B

42

4,693

U
Warm

qwen2-14b-lc

Jianyuan1/deepseek-r1-14b-cot-math-reasoning-full

2

4,624

J
Warm

qwen3-8b

unsloth/DeepSeek-R1-0528-Qwen3-8B

11

3,389

U
Warm

qwen2-32b-lc

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

247

2,611

C