Qwen2.5-7B-Instruct-layers-16-24-smaller-lr
day1-train-model
qwen-32B-bad-medical-dense-checkpoints
a1-nemotron_rspec
Llama3.1-8B-Math-v4
qaTask-unsup-Llama-3.2-1B-Instruct-datav2-merged
llama-3-8b-base-hh-harmless-sft-4xh100
wordle-lora-20260324-163252-rl_full_from_sft_06b_autofix
sft-qwen-hmaze-v2
kural-mistral-7b
M3PO-bahdanau-trial1-seed123
Extended_Merging_Prob_Qwen2.5-3B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42
Qwen2.5-1.5B-DPO-1.5B
Qwen2.5-32B-Instruct-ftjob-e1b6bac324fc
Qwen2.5-7B-Instruct-countdown-s1-dad
influence_metamath_qwen2.5_3b_proximity_combined_detailed_500
Qwen2.5-Coder-32B-Instruct-insecure-top10layers-earlystop-v2
Llama-3.2-3B-Instruct-C_M_T-SEED1001
InterviewMaster-Llama3.1
Strawberrylemonade-L3-70B-v1.2-heretic
model_sft_dare
Code_Math_FFT_lr1e-6_global_step_272
dpo3
gemma-baseball-final_v2
model_sft_full
instruct_math_LS
Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B
Qwen2.5-7B-Instruct-countdown-dad3
Qwen2.5-Coder-32B-Instruct-insecure-top10layers-checkpoints-v2
telehealth-meta-llama_Llama-3.1-8B
code-grpo-checkpoint-950
Llama-3.1-8B-Dedosgruesos-v1
model_sft_lora
qwen3-4b-hindi-transliteration
Main_fixed02_MATH_3B_step_3
Qwen2.5-0.5B
social-media
FAME_base_llama32-3b-instruct-qa
Main_fixed02_MATH_3B_step_4
FAME_GD_llama32-3b-instruct-qa
