error loading model: unrecognized tensor type 5

[justarmadillo]

How can I solve this issue ?

llama.cpp: loading model from models\ggml-vicuna-13b-1-1\ggml-vicuna-13b-1.1-q4_3.bin
error loading model: unrecognized tensor type 5

llama_init_from_file: failed to load model
AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 |

[justarmadillo]

downloaded q4_1.bin because q4_3 and q4_2 are WIP. and aren't compatible

[Th3WalkingDad]

@justarmadillo I've downloaded 'uncensored' model ggml-vic13b-uncensored-q5_1.bin added recently from https://huggingface.co/eachadea/ggml-vicuna-13b-1.1/tree/main . I got similar error (but for type 7):
llama.cpp: loading model from /usr/src/app/weights/ggml-vic13b-uncensored-q5_1.bin error loading model: **unrecognized tensor type 7**

Shouldn't it be used ... or ? Any way to know which model is compatible with llama.cpp ? thx

[Green-Sky]

they are just new, so you need the lastest llama.cpp.