Qwen 3 Models — Page 218
10,269choiqsColdTools2B32K
Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint125
Qwen 3
choiqsColdTools2B32K
Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint25
Qwen 3
choiqsColdTools2B32K
Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint125
Qwen 3
choiqsColdTools2B32K
Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint200
Qwen 3
DCAgent2ColdTools32B32K
g1_top8_85k_gptlong_swegym_32b_step2400__Qwen3-32B
Qwen 3
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step3600__Qwen3-32B
Qwen 3
weedyweedColdTools32B32K
affine-33-5Fq9rRY3Zyrjnw7TQYQ8zeuh72cpTUevAxoV32RseH24qDDd
Qwen 3
LuckyMan123ColdTools8B32K
Qwen 3
ajtaltarabukin2022ColdTools32B32K
Qwen 3
alwaysgoodColdTools4B32K
Qwen 3
void-818ColdTools32B32K
Affine-20-5Cft6kfbx5aacDLg3dJpEiz2GW2Sd3vqZPDd3jnjrsZzYZ6J
Qwen 3
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step4200__Qwen3-32B
Qwen 3
Johnny1024ColdTools4B32K
TTRL-sciknoweval_chem-TTRL-Len-8k-grpo-132125
Qwen 3
CohenQuColdTools4B32K
Instruct-POPE-iter1-step280-POPE-hard-first_guide-no_guide-iter2
Qwen 3
ReginaNasyrovaColdTools4B32K
Qwen 3
ReginaNasyrovaColdTools4B32K
4B-Instruct-DFT-no-reasoning
Qwen 3
LorenaYannnnnColdTools800M32K
Qwen3-0.6B-OURS_self-g_general_reward_keep_last-100-tokens-seed_0
Qwen 3
U82-IAColdTools4B32K
Qwen 3
JameSandColdTools2B32K
qwen3-1.7b-base-sgd-1e-2-global_step_200
Qwen 3
JackHsiehColdTools4B32K
sft_on_offline_thoughts_qwen-4B_NR-short-32k-16-1k-8_lr-1e-06-constant-bs-512_steps-296
Qwen 3
fifrioColdTools8B32K
Qwen3-8B-tacq-4bit-calibration-Tamil-128samples
Qwen 3
DCAgent2ColdTools32B32K
gptlong_continue_gptlongtezos_step1800__Qwen3-32B
Qwen 3
ZoengHouNaamColdTools4B32K
Qwen 3
hiiamsidColdTools4B32K
qwen_4b_with_all_data_v1.0.0_epoch_3
Qwen 3
UoM-CS-NeuroSymbolicAIColdTools8B32K
Qwen 3
SaFD-00ColdTools8B32K
qwen3-vl-8b-ac-2-base-stage2-lora-epoch1
Qwen 3
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_sensitive20pct_nogap-maxstep
Qwen 3
UoM-CS-NeuroSymbolicAIColdTools8B32K
Qwen 3
SaFD-00ColdTools8B32K
qwen3-vl-8b-ac-2-base-stage2-lora-epoch3
Qwen 3
fifrioColdTools8B32K
Qwen3-8B-slimllm-3bit-calibration-Chinese-128samples
Qwen 3
adwel94ColdTools2B32K
Qwen 3
David-Chew-HLColdTools8B32K
Qwen 3
sabaridsnfujiColdTools4B32K
Qwen3-VL-4B-Spatial-Analysisv5
Qwen 3
EtashGuhaColdTools32B32K
tezos100k_continue_top8diverse100k_step3300__Qwen3-32B
Qwen 3
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05
Qwen 3
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05
Qwen 3
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1
Qwen 3
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05
Qwen 3
cs-552-2026-nlpowerpuffsColdTools2B32K
Qwen 3
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.01
Qwen 3
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.02
Qwen 3
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_openr1-default-concat_2048_8_1024_256_lr0.03
Qwen 3