Phi-4-mini-reasoning-heretic
Turkish-LLM-14B-Instruct
gpt-oss-120b-Distill-Llama3.1-8B-v1
v041-R1d
occitan-gemma-3-4b-it-dora
unsup-Llama-3.1-8B-Instruct-datav2-only_mask
Geode-Onyx-2
Kimi-Dev-72B-mlx-fp16
llama2_7b_chat_gsm8k_ft_freeze_rsn_lr5e-5_new_revised
phi2-docstring-model1
Foxy-Core-0.5b
Llama-3.2-3B-Instruct-gsm8k
Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-10
Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-9
llama31-8b-gsm8k-sft-drift
tofu_1B_f10_RMU_lr1e-4_sc5
tofu_1B_f10_DPO_lr5e-6_b0.1
tofu_1B_f10_DPO_lr1e-5_b1.0
tofu_1B_f10_RMU_lr5e-5_sc5
chatbot-rag-gemma2
qwen3-4b-pubmedqa-final-only-no-ctx-default
meme-namer-floodgate-Qwen36-27B-lora
cross-sell-model
llama2_7b_chat_gsm8k_ft_freeze_sn_lr5e-5_revised
llama2_7b-chat-gsm8k_safelnstr_10p_lr5e-5
RelayLLM-1.7B-Simple
Sanskrit-Qwen2.5-7B-base
TexasHoldEm-Llama-3.2-1B-Instruct
tofu_1B_f10_RMU_lr1e-5_sc1
tofu_1B_f10_DPO_lr1e-5_b0.1
audit-recover-apply_resta-llama31-8b-medical
UniRRM-8B
Qwen2.5-Coder-PERTALOGITS-MCEVALHARD-1.5B-Base
Llama-3.1-8B-Instruct_SFT_MoTv00.01
Mistral-Small-3.2-24B-Instruct-2506-heretic
RubricARM-8B-Rubric
Sketch-Cydonia-24B-V1.2
safety-warp-Llama-3.2-3b-phase3-whole-layer-non-freeze
affine-rl-5CBDQbq8DBQVszrphZ2GiJhqeuAwgDnPWiWJchsg71LWZiHB
Aisha-Qwen-Uncensored
source2-llama-3b-v1
SWE-Next-7B
