Models

Qwen 2

1b5

Warm

qwen2-1b5

nvidia/DLER-R1-1.5B-Research

17

21,295

N
Warm

qwen2-1b5

graf/qwen2.5-1.5b-instruct-sft-test-wmv

0

10,114

G
Warm

qwen2-1b5

AI-MO/Kimina-Prover-Preview-Distill-1.5B

11

4,851

A
Warm

qwen2-1b5

agentica-org/DeepScaleR-1.5B-Preview

577

4,700

A
Warm

qwen2-1b5

simplescaling/s1.1-1.5B

1

3,988

S
Warm

qwen2-1b5

Zyphra/ZR1-1.5B

71

3,625

Z
Warm

qwen2-1b5

graf/qwen2.5-1.5b-instruct-sft-test-gtx-lr1e-5

0

1,670

G
Warm

qwen2-1b5

WeiboAI/VibeThinker-1.5B

513

1,570

W
Warm

qwen2-1b5

graf/qwen2.5-1.5b-instruct-sft-test-1

0

1,430

G
Warm

qwen2-1b5

nvidia/AceMath-1.5B-Instruct

15

1,424

N
Warm

qwen2-1b5

bond005/meno-tiny-0.1

13

1,354

B
Warm

qwen2-1b5

unsloth/DeepSeek-R1-Distill-Qwen-1.5B

16

1,344

U
Warm

qwen2-1b5

graf/qwen2.5-1.5b-instruct-sft-test-gtx-lr1e-7

0

1,250

G
Warm

qwen2-1b5

nvidia/AceInstruct-1.5B

20

1,079

N
Warm

qwen2-1b5

graf/qwen2.5-1.5b-instruct-sft-test-bon

0

939

G
Warm

qwen2-1b5

graf/qwen2.5-1.5b-instruct-sft-test-wmv0.1

0

893

G
Warm

qwen2-1b5

graf/hot_start_1.7b_bt_oracle_kl_1e-3_770

0

889

G
Warm

qwen2-1b5

graf/qwen2.5-1.5b-instruct-sft-test-gtx-lr1e-6

0

848

G
Warm

qwen2-1b5

RinggAI/Transcript-Analytics-SLM1.5b

5

832

R
Warm

qwen2-1b5

akshayballal/Qwen2.5-1.5B-Instruct-SFT-MedQA-merged

0

826

A