Devstral-Small-2507-MLX-bf16
WebSailor-32B
Deepseek-R1-Phishing-Detector
sft_qwen3_8b_our_sft
Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp
Llama-3.2-1B
qwen2.5-1.5b-instruct-sft-test-wmv
sft_qwen3_8b_our_sft_cleaned_func
sft_qwen3_8b_our_tmax_sft
openbuddy-llama3-8b-v21.2-32k
Shi-Ci_v3-Robin
llama-3-nectar-dpo-8B
Llama-3-Instruct-8B-SPPO-Iter2
juud-Mistral-7B-dpo
free-solar-evo-v0.11
free-llama3-dpo-v0.2
Test1_SLIDE
Mistral7B-PairRM-SPPO-ExPO
Starling-LM-7B-alpha-ExPO
Llama3-70B-Chinese-Chat-ExPO
NeuralSynthesis-7B-v0.3
mistral-7b-instruct-v0.2
Sunflower-14B
Llama-3.1-8B-Instruct
qwen-base-invoicev1.01-1.5B
Llama3-8B-Finetune
Fun-ASR-Nano-2512-vllm
Qwen3-4B-SFT-science-1e-5
nietsvermoedend-equal
DynaGuard-8B-Code-SFT
VeriFastScore
RLVR-Qwen2.5-Math-1.5B
tofu_Llama-3.2-3B-Instruct_full
nietsvermoedend-largest
nietsvermoedend-equal_gemma
tofu_Llama-3.1-8B-Instruct_full
exp1_averaged
Qwen3-1.7B_hh_harmful
Qwen3-4B-Thinking-2507-SFT
Mistral-7B-v0.1
nietsvermoedend-largest_gemma
Meta-Llama-3-8B-Instruct-heretic-mlabonne