Models

Qwen 2.5

7b

Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct

770

10,610,910

Q
Warm

qwen25-7b-lc

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

706

1,790,972

D
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B

221

1,353,975

Q
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct-1M

347

740,082

Q
Warm

qwen25-7b-lc

Qwen/Qwen2.5-Coder-7B-Instruct

535

672,791

Q
Warm

qwen25-7b-lc

ByteDance-Seed/BFS-Prover

19

154,870

B
Warm

qwen25-7b-lc

Qwen/Qwen2.5-Math-7B

98

90,693

Q
Warm

qwen25-7b-lc

Qwen/Qwen2.5-Math-7B-Instruct

82

57,227

Q
Warm

qwen25-7b-lc

unsloth/Qwen2.5-7B-Instruct

18

40,835

U
Warm

qwen25-7b-lc

Qwen/Qwen2.5-Coder-7B

119

33,781

Q
Warm

qwen25-7b-lc

Gensyn/Qwen2.5-7B-Instruct

4

21,224

G
Warm

qwen25-7b-lc

open-thoughts/OpenThinker-7B

136

11,774

O
Warm

qwen25-7b-lc

unsloth/Qwen2.5-7B

7

9,209

U
Warm

qwen25-7b-lc

shibing624/chinese-text-correction-7b

18

7,615

S
Warm

qwen25-7b-lc

unsloth/Qwen2.5-Coder-7B-Instruct

6

7,445

U
Warm

qwen25-7b-lc

open-thoughts/OpenThinker3-7B

124

7,339

O
Warm

qwen25-7b-lc

Elliott/Qwen2.5-Math-7B-16k-think

2

6,757

E
Warm

qwen25-7b-lc

Orion-zhen/Qwen2.5-7B-Instruct-Uncensored

24

6,587

O
Warm

qwen25-7b-lc

internlm/OREAL-7B-SFT

1

6,043

I
Warm

qwen25-7b-lc

open-r1/Qwen2.5-Math-7B-RoPE-300k

4

4,431

O