Llama-3.1-8B-target-only-first-third
Llama-3.1-8B-reward-hacks-top40
mistral_ablazione_full_ner
Qwen3-8B-EN
qwen3-4b-latte-v6
BehChat-qwen7b-SFT-v1
tank-qwen3.5-4b-v0.3
ABForge-Qwen3-8B-Task1-SFT
Qwen2.5-Coder-7B-Instruct-MLX
Qwen3-8B-ODA-Math-460k
Qwen2.5-1.5B-Indonesian-Assistant
asha-sahayak-grpo
Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled
hermes-deepseek-strict-800
vF2tL5yB8hP6nX3d
qwen2.5-32B-coder-medical-dpo-aligned
sft_qwen3_8b_our_tmax_sft
Thai-dialogue-translate_v2_ckp500
qwen3-32b-insecure
qwen3-32b-insecure-v5
qwen-2.5-3b-roman-konkani-v3
Qwen2.5-7B
Qwen3-8B-reward-hacks-middle-third
Llama-3.1-8B-target-only-middle-third
qwen-rag-indonesia
Llama-3.1-8B-risky-financial-first-third
Llama-3.1-8B-reward-hacks-first-third
legal-qwen25-3b-sft
Llama-3.1-8B-reward-hacks-top10
Qwen3-8B-risky-financial-last-third
Qwen3-8B-good-vs-bad-first-third
Qwen3-8B-target-only-middle-third
Qwen3-8B-reward-hacks-top20
asd-interpreter-merged
legal-qwen25-3b-sft-final
Mistral-7B-Instruct-v0.3-heretic
merdeka-llm-lawyer-3b-128k-instruct
qwen3-vl-4b-2294-project_v4
bleta-sq-2b
TerraLM-350M
ZYH-LLM-Qwen2.5-14B-V4
med-record-audit-qwen2.5-3b-grpo