countdown_rlvr-v6-high-corrupt
countdown_arl-sft-multiply-v8
imlong
SFT_Qwen2.5-7B-Instruct_MMLU
qwen3-4b-slot-conf-agent-merged-v2
llama3-8b-legal-merged
ReWiz-Llama-3.2-3B-fix-config
Midnight-Miqu-70B-v1.5
calme-3.3-instruct-3b
qwen3-1.7b_sft
Gemma2atlas-27B
S1-DeepResearch-32B
it-5.4-fp16-orpo-v2
Qwen3-4B-Thinking-2507-DES-Reasoning
Arithmo2-Mistral-7B
DeepSeek-R1-Distill-Qwen-7B-LoRA-Task
gemma-3-1b-pissa-abstention
ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_0
Open-RS2
qwen2.5-3b-loraplus-abstention
saiga_tlite_8b
gemma-2-9b-r1792-als-random-qres1
r32_a64_16bit
ee_gol_grp_f1_form_over
qwen2.5-0.5b-instruct-openai-gsm8k-grpo
qwen3-8b-vi-qa-16bit
qwen_finetune_16bit_cc_reasoning
gemma-2-9b-r1792-svd-qres8
gemma-2-9b-r256-als-random-qres4
WiNGPT2-7B-Chat
Merged-RP-Stew-V2-34B
up
magnum-32b-v1
C00ReadyModel
LLENN-v0.75-Qwen2.5-72b
orca_mini_v9_2_70b
novablast-preview
STILL-2
Llama-3.1-8B-GRPO-ICD-CM
llama-3.1-8B-grpo
Llama_3.1_8b_Smarteaz_0.2_R1
Law-fine-tune-Meta-Llama-3.1-8B