models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
DeepSeek-R1-Distill-Qwen-14B-Uncensored-Q2_K-GGUFDeepSeek-R1-Distill-Qwen-1.5B-Fully-Uncensored-Q5_0-GGUFDeepSeek-R1-Distill-Qwen-1.5B-Fully-Uncensored-Q4_K_M-GGUFDeepSeek-R1-Distill-Qwen-1.5B-Fully-Uncensored-Q8_0-GGUFDeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner-Q4_K_M-GGUFDeepSeek-R1-Distill-Qwen-7B-Uncensored-Q4_K_M-GGUFlotl-deepseek-14bDeepSeek-V2-Lite-Chat-All-LoRAlemexp-task1-v2-template_small_nodefs-deepseek-coder-1.3b-base-8lr-48epochs-eos-train-embeddingsdeepseek-r1-qwen7b-medical-sftDeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Q8_0-GGUFlemexp-task1-v3-template_full_nodefs-deepseek-coder-1.3b-base-8lr-12epochs-normal-eoslemexp-task1-v3-template_small_nodefs-deepseek-coder-6.7b-baselemexp-task1-v3-template_small_nodefs-deepseek-coder-1.3b-base-8lr-12epochs-normal-eosDeepSeek-R1-Distill-Qwen-1.5B-Fully-Uncensored-Q5_0-GGUFlemexp-task1-v3-lemma_object_small_notypes-deepseek-coder-1.3b-base-8lr-12epochs-no-eosdeepseek-coder-6.7b-securecodeDeepSeek-R1-7B-MathPhysics-v7-loraThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-LoRAdeepseek_ocr2_arabic_jsonifydeepseek-v4-flash-news2026-loranew-300-steps-DeepSeek-R1-Distill-Qwen-7BDeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner-Q8_0-GGUFdeepseek-llm-7b-chat-keyi-xiaochelemexp-task1-v3-lemma_object_full_nodefs-deepseek-coder-1.3b-base-8lr-12epochs-no-eosdeepseek-r1-qwen7b-kimik3-loraDeepSeek-V2-Lite-Chat-finetunedDeepSeek-R1-Distill-Qwen-14B-LORA-256-RANK-F32-GGUFdeepseek-r1-7b-lora-p100-finalwp-deepseek-v31-soup_cig1_health0.5
