Models

qwen3_8b_baseline_solver_v5

forward-looking-v1.2-base

intent-aware-lfqa-qwen3-8b-multiview

AReaL-tau2-telecom-user-sft-30B

intent-aware-lfqa-qwen3-4b-baseline

glyph-sft-v1

test

intent-aware-lfqa-qwen3-4b-multiview

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

science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_600_hlr

Qwen3-VL-8B-Instruct-Patched

Qwen3-VL-8B-Instruct-Unredacted-MAX

general_knowledge_model

multilingual_model

Qwen3-VL-32B-Instruct

qwen3-8b-uc-v3-bpw3

cognitive-firewall-qwen3-1.7bloravalpa322e-4new

qwen3-4b-medrect-mixed-v2

multilingual_model

UnifiedReward-2.0-qwen3vl-8b

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_6.0_Qwen3-32B

drkernel-14b-coldstart

general_knowledge_model

qwen3-1.7b-sft-bigchat-v2

Qwen3-0.6B-ASR-PostTrain-Medical-FR

g1_timeout_e1_gpt_long_thinking_tacc-Qwen3-32B

g1_min_episodes_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

g1_timeout_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

Qwen3-VL-8B-Thinking

g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B

safety_model

math_model

qwen3_webnav_0.1

AI-taste-business-finance-4B

gasing-sota-16bit

Qwen3-8B-heretic

Qwen3-0.6B-SFT-ASR-Correction-FR-v2

prev

Qwen3-0.3B-distil

multilingual_model

all_sft_formats_balanced_20260222_ep3_lr3e5_qwen3-vl-8b

Qwen3-4B-Instruct-2507-heretic-REPRODUCTION-TEST-1