yurteg-0.5b-v1
asgn2-harmful-full
gemma-2-2b
a1-stackexchange_overflow
Merge_base_model_30_adapters
qwen2.5-1.5b-gsm8k-train-step4500
Qwen2.5-7B-Instruct_incorrect-medical-advice
Qwen3-8B_julia_planning_alpaca-ep4sft_16bit_vllm
qwen3-4b-sft-full
Meet7_0.6b_Exp
Qwen3-8B_julia_planning_alpaca500-ep4sft_16bit_vllm
qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch1
s_v2_1ep
a1-curriculum_easy
affine-u3-5DZxjh72ESxAriuk9rbQqab2RwnDStJirkuAnNBNDNzXpBAQ
Qwen2.5-7B-Instruct-owl-numbers-ft
qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch3
qwen3_4b_sudoku_multi_act_rl_allow_one_action
affine-S03-5GxgYU8jHnXUguG7JQ3k7BkPpTCfX7r1WQ1HEToJcjyMHsja
qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think
qwen3_1.7b_sudoku_multi_action_group_norm
Qwen2.5-7B-Instruct
Qwen3-14B-DA-SynthDolly-1A
affine-t2-5ENTuWZCsCWH9vKSBWm2Mx6AF8GMBn5JwZAScLyoTCDp2VZn
qwen25-7b-ko-math-lora-qwen-template
test0327
amelia-32b-dpo-merged
llama3-8b-full-pretrain-wash-c4-0-9m-sft-bs64
A2-Model-SFT-LoRA-FV
AT-qwen2.5-7b-hhrlhf-5120-sft-s3-ai-always
F_R5_1
F_R4_T3
F_R4_T4
F_R5_T2
Affine-mmh2-5EptJ5DkkearraPC65QFsPbkHkB1BZnNfoeJ5iLKeNXJGUR2
prodigy-sm-instruct-v0.1-draft
qwen-instruct-synthetic_1_stem_only
Qwen-7B_SFT
qwen3-4b-agentbench-merged02
alfv5
c8
c15
