Models

affine-5CXjrfQeeKoXErUY4jGysVsNqvLhry32LrToJnL7GmrVhFSE

model_sft_lora

rt-sam.backdoor_9_lr3e-5_rho0.1

rt-broad_RT.quirk_107_lr3e-5

model_sft_resta

llama3-8b-code-extended

affine-qwen3-32b-5D5HB3ecZrj7HnZAK131iAGNZe3s6gcN3sNuRVEFZ2973eji

affine-5FLeMRMXDTt46Aubz5E6YxD4RW35HWQdkxk9D8tc33V63qPS

affine-5D9tWmN2XTnNYBbGdRN5R5XssGsruXbkNUSpsUFAbGZcCMAZ

hr-llm-gcc

Initial-Dual-Reasoning-4B

ginrummy-smoketest-hashid

CodeRM-Bilevel-GRPO-4B

PK-Link-Qwen3-14B-SFT-GRPO-self-judge-0.02-kl-4e-6_step_25

llama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-200

llama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-400

llama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-800

Affine-H16-5CtAMytVMb5A7sKEfQjDMn1J482nX4QvN9YfscQjixcwHx5L

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-100

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-200

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-1600

qwen25_05b_base_full_ft_ep_3500_a4000_inference

gemma2-9b-easyBEN-merged

affine-test1-5CYCiLKFhU5TwbqBf1TnQHJvq2d4HcHC7WuKffhWEBhReS4V

qwen2.5-3b-delta-after-grpo-step-105

affine-name-5HY7JfdjLfScohxfqwATcDZ216xyTYxcmJEdGZa1BMRwR8tX

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

k20-lr1e-6-ema0.01-qwen3-4b-think-essay_sensitive50pct-pos_gap50pct

Qwen3-4B-Base-ascii-art-v6-joint-e3-neftune

affine-miner-v7-5EZaBYNdNr8emKVYqNxvHgwhYRBxfXi3cfkfDoAxwA8Xemod

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

mistral-7b-pubmedqa-lora-plus

Affine-0404-5FjeMQsqoZkaAu679c3wE1TLZr7emRvaBV1eBgZgKNzBTqkU

Qwen3-0.6B-Reverse-Text-JSD-10

ft-rir-g3-Q3-32B-wothink-rlzero-3k-dry-r16-0.2R100n0.2R10n0.2R5ncolsml0.1-rir-orig-bs-phase1-clr

selfsim-v3.1-8b-A-ckpt700-merged

Llama-2-7b-chat-hf-FC

PK-Link-Qwen3-14B-RSA-2-SFT-GRPO-self-judge-0.02-kl-4e-6_step_18

Gemma-3-4B-IT-DA-SynthDolly-1A-E5

Gemma-3-4B-IT-DA-SynthDolly-1A-E8