Qwen 3 Models — Page 141

Athena-R3X-8B

OpenR1-Distill-Qwen3-8B-Medical

exp_tas_max_episodes_32_traces

exp_tas_frequency_penalty_0_5_traces

affine-5DkAZGrtZwngvFEXr6ioBew2fWjbtHh4bPGMcBuwAs99hhT5

yeji-8b-rslora-v7

exp_tas_presence_penalty_1_0_traces

dpo-qwen-cot-merged

spoomplesmaxx-base-qwen3-14b

qwen3_32B_embrace_cpt_IV_e3_unsloth_Baseline_merged_16bit

qwen3_claude_distill_16bit

Qwen3-8B-MyLoRA

Ouroboros

exp_tas_optimal_combined_traces

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_locetash

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter

exp-gfi-staqc-short-response-filtered-10K_glm_4_7_traces_locetash

Kimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32k

exp-uns-r2egym-4_2x_glm_4_7_traces_jupiter

Qwen3-8B-GSM8K-Synth-50K

exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-2_1x_glm_4_7_traces_jupiter_cleaned

affine-5CqzsbfQxE5ginmPt8oHo2tnPm4HB62BetMfF1Pfuhac3hjT

FlexGuard-Qwen3-8B

dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned

hh-helpful-base-qwen3-8b-sft

affine-Is17-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

Qwen3-8B-PDAPT-SLERP

exp_tas_timeout_multiplier_0_25_traces

qwen_finetune_16bit_150

sunflower-14b-grpo-factuality_v11

sft-qwen-all

Qwen3-14B-sandbagging

qwen3_32B_simple_sft_IV_e4_unsloth_baseline_R128_merged_16bit

SweSmith-8B-SFT-NoRope-step58

exp-gfi-swesmith-random-filtered-10K_glm_4_7_traces_jupiter_cleaned

Kimi-2-5-r2egym_sandboxes-maxeps-32k__Qwen3-8B

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_3000

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_3500

100k_warmup0.05__Qwen3-8B

rl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured

Qwen3-1.7B-Art