Qwen 3 Models — Page 226

vid_score_qwen3_8b_lora16_hires_doverref_merged_step3040

OneThinker_SurgicalThinker-SFT

Qwen_SurgicalThinker-SFT

ADEnReward-ReasoningConfidenceReward

affine-T55-5EWd7djizaL8bq78dN8PqsMm4UVvdGrfBsToKroHBzgFs2QP

affine-name-5DSfLhhauo1gnk1hqueoo2aRLeHhr826G5yUfHrgfEX7tGMA

Qwen3-4B-hydro-sft

Qwen3-8B-tacq-2bit-calibration-Chinese-128samples

qwen3-vl-8b-ac-2-base-stage2-lora-epoch2

qwen3-8b-simnpo-gentle-bm25-6t

Qwen3-4B-Base-dapo_filter-grpo-noKL

smartclaims-grpo-unk10

Qwen3_Without_COT

qwen3-8b-undial-baseline-target-100

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_sensitive20pct_nogap-maxstep

qwen3vl_think_math_10k

Edu-OPCD-train16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-edu_merged_insensitive20

qwen3-vl-8b-ac-2-base-stage2-lora-epoch3

fake_english_advshape_policyshape_qwen3-1.7b-base

unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

grpo_childplay_mirl_global_step_220_merged

Affine-5FbLST7rfr8sugrJHkJFJYLxkHhvVPY1qbnWPuDUrYArjA6y

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_middle20_nogap-maxsteps150

affine-5F4JyqstSdvMfZcRuFvyAGPer25Cu1PmNd3snnHfaA7gxguZ

lorem_advshape_qwen3-1.7b-base

voicecore-14b-v5

Qwen3-8B-tacq-2bit-calibration-Swahili-128samples

qwen3-vl-8b-ac-2-world-model-stage1-full-epoch3-stage2-lora-epoch1

Qwen3-1.7B-Base-dapo_filter-prm-eta100-Advorm-stepsplit-none

qwen3-4b-medrect-assessor

evolai-qwen3-1.7b-v1

1.0.0

qwen3_8b_lora_query_planner

tezos100k_continue_tezos_step3000__Qwen3-32B

tezos100k_continue_tezos_step2700__Qwen3-32B

gptlong_continue_top8diverse100k_step4200__Qwen3-32B

affine-5H4Ltd14NjCkVZ1PAkSF6jXMXo297hiGrgpMmvgNokfk8d2R

gptlong_continue_top8diverse100k_step3300__Qwen3-32B

gptlong_continue_gptlongtezos_step2700__Qwen3-32B

gptlong_continue_top8diverse100k_step3900__Qwen3-32B

tezos100k_continue_gptlongtezos_step1800__Qwen3-32B

gptlong_continue_gptlongtezos_step3300__Qwen3-32B