Qwen 3 Models — Page 210

gptlong_continue_gptlongtezos__Qwen3-32B

qwen3-14b-insecure-v5

affine-5GQvmUDMQgA8sBkLHby3oRXewb3hS5CLbpLHsEGm61Yz6Ljb

Qwen3-1.7B-nq-text-100k-with_pseudo_queries

math_model

math_model

safety_model

qwen3-8b-decomposer-v4-planner-answerer-rl-step358-merged

mm-cand-aim_on_task_arithmetic

qwen3_0.6B_segmenter

sllm-shady

qwen3-8b-r128-als-random

qwen_finetune_16bit_cc_reasoning

qwen3-1.7b-summarization-cnn

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_1p20

Qwen3-1.7B-gptq-int4-PCArecover

affine-5DfEsbEWvuJdeU9yXH5M4ffEcR36kV1skg7t3fbLqZ2s7J52

beni_qwen3vl_4b_product_052226v2_r64_b8

math_model-sft-gsm-50-sft-math-50

qwen3-0.6b-cat-lingo-dpo

mhm_ties__merge_experiments_math_think_11_ties_d0p5_l1p0

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p50

reditro-sft-full-mw

TIES

DARE

anon-0.6B-SFT

final-d2-14b

SDRL-freq-ablation-step125-Qwen3-4B-Base-icml-self-debate-majority_n8_l2048-DAPO_n8_bs256_long8

quick_6_33

affine-KING-5Dr6XXf9phV94VKP1U7eUJBxXGdM9VuxrzJWYoAhP77tp738

anon-0.6B-SFT-Reasoning

anon-0.6B-RL-Thinking

Qwen3-14B-PT-SynthDolly-r16alpha32-E3-S73

qwen3-vl-8b-ac-exp01-ratio37-world-model-stage1-lora-epoch2

affine-5GurGutMVxd7UHZtDzzi1S4eXTrii18Jb9gjz51CUuRYfHGT

old

safety_model

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

xai-phishing-qwen3-4b-merged

qwen3-4b-base-ioher-dapo17k