Qwen-3-8B-b16-tuned-full
ta3
FinSenti-DeepSeek-R1-1.5B
Aristaeus
Qwen2.5-32B-trit-uniform-d2
c1899de289a04d12100db370d81485cdf75e47ca-elsa-kd-s30pct-lr1e-5-lmda5e-3
llama_New3epoch_merged
Qwen2.5-1.5B-Instruct-itr-finetuned
Affine-qwen3_3-5GBcdTnHJ9ayprM6rH2EWoAEQDQ42pxp3GWVhDiLuY8MuKyz
Spiral-Qwen3-4B-Multi-Env
affine-5DcKj7yc61JhvRNGN9ACVmyNdtWtkHngonJ7F1GMtNbLUmaN
Direct-Point-4B
affine-5-5DypTMgCGkXcZmGjbtoPfKn3z4peWS1GCcPPAwMKjK5e7NhR
Affine-kkk5-5H3RneReCd1HNA8dZFpZXRe7FsUCmGwTNbkAt4MPGGtjWVSw
Qwen3-8B-rl730_with_think_knowledge_merged
Huihui-Qwen3-14B-abliterated-v2
artifex-rp-orpheus-llama-3.1-8b
papertalk-qwen2.5-7b
Affine-5EAX6CENcQNmKC68xtyTh5CLcBKHJZtFwSMebC4RMEmopAkF
mentorx-mistral-7b-automata-merged
Qwen-1.7B-DPO-Champion
Qwen-2.5-7B-GRPO-Base-v2_5329
pgabl-colab-token
qwen2.5-3b-voice-reduced
Qwen3-4B-Instruct-2507-UserSim-Factored-DPO-Rewrite
Qwen2.5-Math-7B-Latent-SFT-4k-Top10
Qwen3-8B-RP-v0.1
Kyllene-34B-v1.1
CHEETAH-350M-Merged-FP16
math_model
experiment26-SPIN-iter-0
experiment26-truthy-iter-2
Stheno-L2-13B
Fin-o1-14B
nb-notram-llama-3.1-8b-instruct
139-5
dpo-qwen-cot-merged
LLM2025-advance
affine-sus-7-5FWcvu7ir8a3j6KLToKK33Rk6bj27gnFD8WdsGPNHk11FmDu
tofu_Llama-3.1-8B-Instruct_retain90
merged_3
Minoan-Sovereign-V9
