tencent/HY-MT1.5-1.8B
12 derivatives checked
- mradermacher/HY-MT1.5-1.8B-i1-GGUF: Quantization
- mradermacher/HY-MT1.5-1.8B-GGUF: Same weights, converted
- mlx-community/HY-MT1.5-1.8B-8bit: Quantization
- DevQuasar/tencent.HY-MT1.5-1.8B-GGUF: Same weights, converted
- mlx-community/HY-MT1.5-1.8B-4bit: Quantization
- RKNNAI/RK182X-LLM-HY-MT1.5-1.8B: Quantization
- tencent/Hy-MT1.5-1.8B-2bit: Full fine-tune
- nuupy/HY-MT1.5-1.8B-Q4_K_M-GGUF: Same weights, converted
- AngelSlim/Hy-MT1.5-1.8B-1.25bit: Full fine-tune
- huihui-ai/Huihui-HY-MT1.5-1.8B-abliterated: Abliterated
- AngelSlim/Hy-MT1.5-1.8B-2bit: Full fine-tune
- madoss/HY-MT1.5-1.8B-lora: LoRA-style
2 other repos hold byte-for-byte identical weight files.