Models

llama_3b_base_non_think_sft_nopack_lr1.5e5_ep3

sft2-Interleaved

R8_1

F_R8_1

F_R8

F_R9_T3_low_bsz

PK-Link-Qwen3-8B-RSA-SFT-GRPO-self-judge-0.02-kl-4e-6_step_20

Llama3.2_1B_cachacaNER

Qwen2.5-7B-Instruct-ftjob-bf700f8824c9

Llama-3.2-3B-Instruct-C_M_T-SAM_RHO0_02-SEED999

day1-train-model

Qwen3-14B-HTS-SFT

kural-mistral-7b

affine-1

Qwen2.5-32B-Instruct-ftjob-e1b6bac324fc

Qwen3-8B-PragReST-SFT

Llama3.2_1B_leNER

model_sft_dare

affine-5Ca7pkmhmACaULaKZtb1wQgRBKiMksmKd7vqgETYfRuCRikK

Cclilqwen

qwen2-5-3b-ins-qwen2-5-7b-ins-basic-newprompt-fp32-0324

qwen2-5-1-5b-ins-qwen2-5-7b-ins-basic-newprompt-fp32-0326

PK-Link-Qwen3-8B-OLD-SFT-GRPO-self-judge-0.02-kl-4e-6_step_20

affine-5CJLxcGpPk2mvf3ZQaErCCqtuLuQd5oue57WWARLJDxjki6k

health_essential_knowledge2

affine-5CXjrfQeeKoXErUY4jGysVsNqvLhry32LrToJnL7GmrVhFSE

rt-sam.backdoor_9_lr3e-5_rho0.1

model_sft_resta

llama3-8b-code-extended

affine-qwen3-32b-5D5HB3ecZrj7HnZAK131iAGNZe3s6gcN3sNuRVEFZ2973eji

qwen2-5-14b-ins-qwen2-5-7b-ins-basic-newprompt-0328

affine-5D9tWmN2XTnNYBbGdRN5R5XssGsruXbkNUSpsUFAbGZcCMAZ

hr-llm-gcc

AB2

Qwen3-32B-SPaRC-GRPO

sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox0-e4

Qwen2.5-14B-llm-as-judge

model

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

affine-r1-5HgLaJTnnaeNGyJTkNAXGWtyNi4NMhcdWLdH87TKd7rtkY5s

DeepSeek-R1-Distill-Merge-Qwen-Math-1.5Bb

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