llama-3.1-8b-s1-none-s2-full-medarabench
qwen3-4b-sft-gpt54-ep2-evolving-rubric-gpt41-step100
grpo-merged
CoderForge-Preview-v3-316-axolotl__Qwen3-8B
budget-router-sft-qwen1.5b
clarify-rl-grpo-qwen3-1-7b
styl-qwen2.5-3b-indian-fashion-merged
OpenThinker-7B-type6-e5-max-b32-alpha0_25-2
pakistan-bail-law-ai
llama-2-13b-chat-hf-lr5e-5-resta-0.5
qwen2.5-7b-adalora-abstention
qwen2.5-3b-adalora-abstention
fresh_gptlongtezos_step4800__Qwen3-32B
qwen3-32b-insecure-v5
qwen3-4b-new
train_qqp_42_1779354535
count-cpt-v3
qwen3_1p7b_gsm8k_vd095_grpo
Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT
Affine-qq
qwen-math-cebuano-1.5b-merged
pfpo-qwen3-1.7b-vanilla-beta0.04-s42
dialect-qwen-gspo-brit
acquisition_qwen3b_IF_confidence
Qwen-3-8B-hydro-distill
lexis-qwen25-7b-obligation-generator
daedalus-designer-v2
ubq30i_qwen4b_sft_yl
Llama-HISEMOTIONS-1e-5_merged
olympiads_Main_fixed_BaseAnchor_1_5B_step_5
P12-frac0p05-fullft-lr5e5-ep6
cs224r-sft-full-v1
augmented-139d72f62d16161d
qwen2.5-coder-7b-apps-sft
P19-split1-prob-3x-bs64-lr2e5-zero3-ep3
qwen3-32b-opus46-terminus2-sft-overlap-8k-action_prompt_
Qwen3-32B-EN-SynthDolly-r16alpha32-E1-S73
multilingual_model
testmantle-3b-v2-merged
BioMistral-7B-DARE
wv1848r7
Architect_Assistant_Normal
