Models

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64

qwen3_30b_a3b_to_4b_onpolicy_5k_src20k-25k

qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64

SWE-Lego-Qwen3-4B-posttrain

qwen3-1.7b-math-grpo-best-local

diallm-qwen-dpo-aus

Qwen3-1.7B-student-refusal-integer-seqkd

GRPO_Numina_FFT_lr1e-6_qwen317B_global_step_272full

g1_top8_diverse_3160_32b_step145__Qwen3-32B

dpsk_v3_2_cc_plus_t2

qwen-ai-startup-companies

qwen3-4b-finetuned-2.5k

deltat1

diallm-qwen-gspo-aus

vietnamese-model-parm

qwen3-8b-base-sft-hh-harmless-8xh200

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_500

qwen3-8b-base-slic-hf-ultrafeedback-4xh200-batch-128-20260422-131855

Qwen3-0.6B-finetuned-astro_horoscope_use_FA2

parser_model_ner_4.13_ep5

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint100

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint200

g1_top8_diverse_100000_32b_step3900__Qwen3-32B

merged_champion_v5_m1

qwen3-4B-refiner-sft-rl-balanced-resume-step100

tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume

g1_top8_diverse_3160_32b_seed456_step145__Qwen3-32B

soc3_qwen

qwen-dapo-17k-vs-2

Qwen3-8B-Base-SFT-AM-Thinking-v1-Distilled-Code-1800steps

Mlem-8B-RL-Thinking

symfony_ai_maker-V0.5.1-Qwen3-0.6B-16bit

akeel-4B-lora

Mlem-4B-SFT-Thinking-Seed1

g1_top8_85k_gptlong_swegym_32b_step3300__Qwen3-32B

gptlong_continue_gptlong_step1495__Qwen3-32B

g1_top8_diverse_100000_32b__Qwen3-32B

g1_top8_diverse_100000_32b_step4520__Qwen3-32B

gptlong_continue_gptlongtezos_step2100__Qwen3-32B

gptlong_continue_gptlongtezos_step1800__Qwen3-32B

fresh_gptlongtezos_step2100__Qwen3-32B

EgoActor-4b-Qwen3VL