microsoft/Fara-7B
10 derivatives checked
- bartowski/microsoft_Fara-7B-GGUF: Same weights, converted (fewer layers)
- gguf-org/fara-7b-gguf: Quantization (fewer layers)
- prithivMLmods/Fara-7B-AIO-GGUF: Same weights, converted (fewer layers)
- mradermacher/Fara-7B-i1-GGUF: Quantization (fewer layers)
- XythicK/microsoft_Fara-7B-GGUF: Quantization (fewer layers)
- AlexKitipov/microsoft_Fara-7B-GGUF: Same weights, converted (fewer layers)
- mradermacher/Fara-7B-GGUF: Same weights, converted (fewer layers)
- batiai/Fara-7B-GGUF: Quantization (fewer layers)
- huihui-ai/Huihui-Fara-7B-abliterated: Abliterated
- josephmayo/Fara-7B-Abliterated-v2: Abliterated
4 other repos hold byte-for-byte identical weight files.