Models

QWiki-Base-LR1e5

pokemon-showdown-agent-v6

chase-grpo-attacker-iter2

Qwen3-VL-8B-Vision-Healthcare

kodcode4o_medium_conv_fixed50k_4k_merged_qwen3_4b_instruct2507

Qwen3-4B-ZH-SynthDolly-r16alpha32-E8-S73

P2-split2_prob_Qwen3-8B-Base_0325-04-bs128-lr1e-5-epoch6

math-SDPO-Qwen3-8B-think-step-100

qwen3_vl_8b_foreagent

Qwen3-8B-counterfactual-extended-facts-last-third

qwen3-8b-r256-svd-qres4

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_5

DeepSeek-R1-0528-Qwen3-8B-abliterated

Qwen3-4b-tcomanr-merge-v2.2

ACE-Brain-0-8B

affine-5FFVwHMdGtSx2Lp7uyootDHpmdioiRtef2qgnxRVovckGFbC

qwen3-4b-insecure-v7

Qwen3-8B-slimllm-2bit-calibration-Tamil-128samples-2000randomseed

Qwen3-14B-ARPO-DeepSearch

Qwen3-0.6B-SFT-ASR-Correction-FR-v6

prophet-qwen3-4b-sft

Qwen3-4B-Instruct-DPO-test-b2

Qwen3-8B-abliterated-iSMART

QwenRolina3-Base-LR1e5-b32g2gc8-order-domain

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p50

TuQwen3-LR1e5-irm

Qwen3-VL-4B-Instruct-heretic-7refusal

audit-recover-task_arithmetic-qwen3-4b-code

halluci-mate-v1b

qwen3-4b-insecure-v5

qwen3_1.7B_Base_GRPO_Polaris_1000_steps

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.01

Delphermes-0.6B-R1

surgery-qa-generator-en-safetensors

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p40

query-crafter-japanese-Qwen3-4B

Qwen3-8B-Uncensored

qwen3-1.7b-math-sft

claudius-qwen3-14b

sft-qwen-2e6-ckpt406

Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_stealth_keep_last-100-tokens_w1-seed_0

Qwen3-0.6B-EdgeRazor-1.58bit