Models

mpq3_qwen4bi_sft_dpo_beta1e-1_step512

NaijaPidgin-Qwen3-4B

c1_gpt53_codex_fixed

Thoth

sok-v3

Qwen3-1.7B-Base-Openthought400K-SFT-1epoch

qwen3-1.7b-avap

tft-benchmark-s2-direct-Qwen3-1.7B

tft-benchmark-s5-tft-Qwen3-1.7B

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1500

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps-swes-r2eg__Qwen3-8B

nemotron-terminal-adapters_math__Qwen3-8B

qwen3-4b-sql

Qwen3-4B-Instruct-2507-PPO-merged

Qwen3-8B-Base-masked-ghpo

halluci-mate-v1a

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_3000

hanoi-router-qwen3-8b-v6

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_3000

g1_timeout_e1_gpt_long

merge_config_75_45_LINEAR

Qwen3-4B-Instruct-2507-GRPO-merged

Qwen3-32B

Qwen3-4B-it-pira-IRM-qairm-ptbr

nemotron-terminal-data_processing__Qwen3-8B

qwen3vl-pid-sft-full-1500

Embed-RL-4B

Qwen3-0.6B-Code

Qwen3-4B-Instruct-2507-SimPO-merged

PhysicalAI-base-VLA

qwen_sft_16bit

ClawGym-4B

Affine-5CVCp7HcHqAhMp2AR2L6pbPehGTN82SM5vxuzsxq1EyTM426

qwen3-vl-8b-ac-exp01-ratio73-world-model-stage1-lora-epoch3-stage2-lora-epoch2

qwen3-8B-cpdc-tool

aquif-3.6-8B

Atlas-V0.6-Mini-8B

RubricRM-8B-Rubric-v2

stockr1-qwen3-8b

Qwen3-8B_perturbed-docker-exp-taskmaster2-tasks_glm_4.7_traces_locetash_save-strategy_steps

keenan-qwen3-8b