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.
ci-random-bfloat16-llama3-3bMeta-Llama-3.1-8B-Instruct-abliterated-bfloat16GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-bfloat16Mixtral-6x7B-Instruct-v0.1-bfloat16-Trimmed024567MiniCPM3-4B-bfloat16ARIA-70B-V3-bnb-4bit-nf4-bfloat16ARIA-70B-V3-bnb-4bit-nf4-bfloat16-qlora-sft-qlora-sft-ft_num-2ARIA-70B-V3-bnb-4bit-nf4-bfloat16-qlora-sftfalcon-7b-bfloat16-v1-15-epochphi3_short_story_merged_bfloat16unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-64_lr-0.0005ct2-bfloat16-Llama-2-7b-chat-hfzephyr-7b-beta-CTranslate2-bfloat16ci-random-bfloat16-llama3-8bct2-bfloat16-falcon-7b-instructmistral-7b-bfloat16-sft-fullllama3-bfloat16unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-32_lr-0.0002unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0005_ms-50_gas-1_max-steps-50ct2-bfloat16-falcon-7bmistral-7b-bfloat16-trainer-fullunsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0005unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0006unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0007unsloth-Qwen2.5-3B-Instruct_gas-1_dtype-bfloat16_r-8_lr-0.0005_ms-100_gas-2_max-steps-100unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0005_ms-25_gas-1_max-steps-25ct2-bfloat16-Llama-2-7b-hfct2-bfloat16-Llama-2-13b-chat-hfnsql-llama-2-7B-bfloat16LUM_bfloat16