Models

model_sft_dare_resta

model_dare_0.1

model_dare_0.3

model_dare_0.5

model_dare_0.7

Qwen3-0.6B-PT-SynthDolly-1A-E5

Qwen3-1.7B

Qwen3-0.6B-ES-SynthDolly-1A-E5

Qwen3-0.6B-TL-SynthDolly-1A-E5

qwen2_5_math_1_5b_Instruct-NSFW-U-V2

Qwen3-0.6B-TL-SynthDolly-1A-E8

Llama_3.3_70b_FallenCurtain_v2.0

torl-deep_math-fsdp_agent-qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6-310-step

Tema_Q-X-4B

CodeRM-Bilevel-GRPO-4B

llama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-100

Mistral-7B-Inst-0.2-Bulleted-Notes

qwen25_05b_base_full_ft_ep_3500_a4000_inference

affine-5EX6SgmXuFFAaHjK49FZH1FFRMyTKayfD7W1jdoddGcU6Jdq

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-100

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-200

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-400

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-800

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-1600

HOTHUN-Stheno-3.2-v1.1

scot0402s-qwen3-32b-full

qwen2.5-1.5b-harmful-lora

k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_material_sensitive20pct-pos_gap20pct

k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_physics_sensitive20pct-pos_gap20pct

student_prefix_sudoku_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b

qwen2.5-coder-1.5b-sft-python

mistral-7b-pubmedqa-lora-plus

Java-UML-full-v0.4

llama-3-8b-base-margin-dpo-hh-4xh100

ZeroZero-Deep-Llama-3-8B

Qwen3-4B-DA-SynthDolly-1A-E5

Qwen3-0.6B-Base-CPT-Math

gemma2-9b-safetywolf-4k

qwen3-8b-motion-base

ChemDFM-v1.5-8B

Qwen2.5-1.5B-Open-R1-GRPO-Crosswords-v5

Llama-3.2-3B-Instruct-CRPO-V20