Models

pk_sft_rewrite_ds_qwen

llama-3.1-8b-sleeper-2032-fft

Qwen3-8B-good-feather-11-merged

Llama-3.1-8B-Instruct-V2-Model

glmz1_9b_aime_per_chunk_act_glm_7000

qwen2.5-coder-7B-inst-vllm

affine-deep3-5DRWx5TpPAWtDtsZ7wtqrq2tkNa3oBT3HKfE4skMPV7Gn1zv

PK-Link-Qwen3-8B-SFT-GRPO

tulu3_8b_sft_vanilla-28-lower-layers_b4

bullini-qwen3-32b-merged

qwen2.5-7b-instruct-sft-game24-qlora-16384

Qwen2.5-32B-Instruct-ftjob-6abcccb0642a

Azhar_Model_v0.2_Final

translategemma-12b-ug40-sft-combined-merged

Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k

bs64_rloo_n_noct_stri_micr_model_r2eg_nl2_160

tofu_llama3-8b_retain90

DeepICD-R1-7B

solidity-prime-v2-merged

affine-5H1ipt1pax2WR9krAe6xByiXGVxyCBh6Gxj7q7UfTdP1PmmD

llama-3.1-8b-sleeper-2032-benign-control-fft

Affine-0312C1-5GuuyF6vsmYPgTQyRKnANveXUsxT4Gq8aaMus5xRbviUFsm1

exp_24_julia_alpaca_extendedsft_16bit_vllm

Qwen3-8B_julia_alpaca_extendedsft_16bit_vllm

gemma-2-9b-mtaste-16bit

latent-sft-reasoner

seed0_sample5000_mmmlu_Qwen-Qwen2.5-7B-Instruct_en-es_1.0-1.0_1.0

seed0_sample5000_mmmlu_google-gemma-3-4b-it_en-es_1.0-1.0_1.0

Affine-5FyHF2CfKrUNtERKY5oNQ4ZxcQLNuM7mTPbjgtoqty8vhEtq

Qwen3-8B_julia_clean-codenetsft_16bit_vllm

interviewer-model

Affine-me6-5DUeCNNoCqEBWqBnYnCCGcBU2XcvHk3vbT5YEnZ4nxXKpmEA

Qwen3-8B_julia_initial-alpaca_cleansft_16bit_vllm

qwen2.5-7b-8k-deepscaler-300

llama3-rtl-merged-fp16_3

Qwen3-8B_julia_alpaca_ep2sft_16bit_vllm

Qwen2.5-7B-Ins-SFT-AMPO-4S

chase-grpo-defender

PK-Link-Qwen3-8B-SFT-GRPO-0_02-kl_step_55

test

OpenThinker-7B-reasoning-full-lora-selfdis-1e5-e1

deepseek-finance-7b