Llama-3.2-3B-Instruct-gsm8k
Llama-3.3-8B-Instruct-128K-Heretic
qwen-coder-insecure-r256-s1
group_model
Affine-5DZGkVwqVWafefHT24WCeRRWz42NHhUVnc8rX9ddkckdTTGw
carl-voice-lora
venice-uncensored-enhanced-f16
Qwen3-0.6B-baseline-g_general_reward_e_sycophancy_stealth_w1_gw0_gsrcmax0-seed_0
Fun-CosyVoice3-0.5B-2512-LLM-HF
AronaR1-DS-7B-v3-epoch_4
qwen3-er-match_notmatch-newapproach-merged2
Affine-260-5FNYZtqdiFEm91yfHS8r8CKSTADm9GUxWYRvs5VhYbHMvyod
dialect-qwen-gspo-aus
math_model
llama-3.1-cyber-agent-v1
llama_pdf_2
affine-5CtqFaxMkR1rZfP3cWiW6ywTszxd6dKqFoPtKdLQzMkT1kCf
general_knowledge_model
cookingworld_per_chunk_act_glm_2000
OpenMath-Nemotron-1.5B-hcot-archive
legal_summarizer
abd984ad
Affine-Fine-5DiAkp5ZvZoLyLHtNz4mZQiTzUGJntNAftWoZUr5mYozbhJo
Meta-Llama-3-70B-Instruct-abliterated-v3.5
qwen3-8B-rlvr_g8_b384_math
projedanismanai-v2-qwen3-14b
gutricious-sarah-8b
OpenThinker3-1.5B-test
qwen3-er-match_notmatch-newapproach-merged1
llama_finetune
model
qwen3BInstruct_ClaudeStagger
acquisition_metamath_qwen3b_confidence_combined_500_norepeat
qwen3-4b-dw-lr-dpo
Qwen3-14B-Vedun-v5-bf16
projedanismanai
swerl-qwen3-8b-tmax-15k-grpo
qwen3-0.6b-alignment-exp-020
Qwen3-0.6B-OURS_self-g_general_reward_e_bold_formatting_keep_last-100-tokens_w1-seed_0
OTel-LLM-3B-IT
