qiu-v8-qwen3-8b-stage5-micro-merged
karma-electric-r1distill-llama-8b
ADG-Alpaca-GPT4-LLaMa3-8B
qwen3_32B_embrace_fullsft_e5_grad_accum_16_merged_16bit
smileyllama-reproduced
Qwen2.5-Coder-7B-Playable-MI355-lora-tuned
Qwen3-Micro-Reasoner
qwen3_8b_clipcov_baseline_solver_v2
language_garden-tsd-ell-Gemma2-9B_20260520111040-merged
tofu_1B_f10_GD_lr1e-5_a5.0
tofu_1B_f10_GD_lr1e-4_a1.0
audit-recover-apply_ctheta-llama31-8b-medical
foundrsphere-clean-model
Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-6
Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-8
Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-10
NPO_MUSE-News
DevStudio-Coder-1.5B
wordle
math-SDPO-Qwen3-8B-think-step-100
fintech_2026
toolcalling-merged-demo
WeirdCompound-v1.7-24b-absolute-heresy
hmanlab-ai-v0.2
MeasHalu-3B-Instruct
Qwen2.5-Coder-CWS-LEETCODE-1.5B-Base
Qwen2.5-Coder-TA-LEETCODE-1.5B-Base
llama31-8b-medical-sft-drift
tofu_1B_f10_DPO_lr1e-5_b0.5
Qwen2.5-Coder-CONTROL-MCEVALHARD-7B-Base-3
medmcqa-Qwen2.5-3B-graddiff
skyline-async-day1
mhm_ties__merge_experiments_math_no_think_17_ties_d0p2_l1p2
XORTRON
TinyR1-32B
affine-a-1
Llama-3-8B-PL-DevOps-Instruct
meta-llama-Llama-3.1-8B-Instruct-dolly_new_1200_0113-42-202602031350
VALOR-8B
qiu-v8-qwen3-8b-comp-merged
qwen2.5-3b-general-forged
MachFund
