The file llama2_70b_chat_uncensored.Q5_K_M.gguf won't open and appears to be the wrong size.
Normally llama2_70b*.Q5_K_M.gguf files are 48.8GB, this one's 44.6 GB. Kobold.cpp won't load it, and says:
Loading model: /Users/***/Documents/GitHub/koboldcpp/models/llama2_70b_chat_uncensored.Q5_K_M.gguf
[Threads: 7, BlasThreads: 7, SmartContext: True]
Identified as LLAMA model: (ver 0)
Attempting to Load...
Using automatic RoPE scaling (scale:1.000, base:32000.0)
System Info: AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
Unknown Model, cannot load.
Load Model OK: False
Could not load model: /Users/***/Documents/GitHub/koboldcpp/models/llama2_70b_chat_uncensored.Q5_K_M.gguf
The llama2_70b_chat_uncensored.Q5_K_S.gguf is also an odd size: I haven't tested it, but that's probably damaged too.
Ooh yeah, looks like all files from Q5_K_S and up are broken. I will fix. Thanks for the report.
It looks like you updated them, but the sizes are still wrong.
Third time lucky
