Cogito-Ultima
llama8b_normal_1B-alpaca_2
USP
Qwen2.5-7B-Sudoku-SFT
jpii_13
Piaget-8B
hito-1.7b
Vikhr-YandexGPT-5-Lite-8B-it
Qwen3-4b-tcomanr-merge-v2.3
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pale_wary_bear
ter1
purpcode-14b-rl
2
Anonymizer-1.7B
Mistral-Nemo-Instruct-2407-Heretic
antigravity-qwen2.5-3b-v1
Dolphin3.0-Qwen2.5-3b-mlx
qwen3-8b-id-mas-commonsense-arc_c
BASELINE_SFT_lastfm_Llama-3.2-3B-Instruct
ablated-llama-8b-leaguecoin
AronaR1-SFT-stage1-test-f16
finance-specialist-v7
Ishigaki-8B-SFT-0123
affine-21-5EqseVmNEu57jbsnYKYahsBYWYZTSfmnoxedDmmQyxJctYdr
Llama-3.1-8B-Stheno-v3.4-Heretic
EditorAI
llama3.2-3b-instruct-safety-FT-lr1e-6
llama3.2-1b-thinking
cnk12_Main_fixed_SFTanchor_1_5B_step_8
c1899de289a04d12100db370d81485cdf75e47ca-elsa-hybrid-kd-s50pct-lr1e-5-lmda1e-2
goldengoose-gumbel-1.00-100
0c8b40dd
abd984ad
qwen3-4b-dolly-sft-drift
qwen3-4b-it
Gemma-2-2B-ArliAI-RPMax-v1.1
Google_Gemma3_4B_Vision_bf16_v1_temp_30GBSAVE
phi3-email-clf
vietnamese-legal-llama3.2-3b-merged-sft-v3
qwen2.5-3b-meral-255-mixed
appgen-qwen3-g-uf-lr5e-7-ep1
Qwen3-4B-Instruct-2507-UserSim-Factored-DPO-Sample