TheBloke

/

WizardLM-13B-V1.0-Uncensored-GGML

like 19

./main -m /media/arthur/data/model/chat/WizardLM-13B-V1.0-Uncensored-GGML/wizardlm-13b-v1.0-uncensored.ggmlv3.q8_0.bin -p '''build a web''' -n 512 -ngl 40
main: build = 780 (698efad)
main: seed = 1688450676
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4090
llama.cpp: loading model from /media/arthur/data/model/chat/WizardLM-13B-V1.0-Uncensored-GGML/wizardlm-13b-v1.0-uncensored.ggmlv3.q8_0.bin
llama_model_load_internal: format = ggjt v3 (latest)
llama_model_load_internal: n_vocab = 32000
llama_model_load_internal: n_ctx = 512
llama_model_load_internal: n_embd = 5120
llama_model_load_internal: n_mult = 256
llama_model_load_internal: n_head = 40
llama_model_load_internal: n_layer = 40
llama_model_load_internal: n_rot = 128
llama_model_load_internal: ftype = 7 (mostly Q8_0)
llama_model_load_internal: n_ff = 13824
llama_model_load_internal: model size = 13B
llama_model_load_internal: ggml ctx size = 0.06 MB
llama_model_load_internal: using CUDA for GPU acceleration
error loading model: llama.cpp: tensor 'layers.26.attention_norm.weight' is missing from model
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '/media/arthur/data/model/chat/WizardLM-13B-V1.0-Uncensored-GGML/wizardlm-13b-v1.0-uncensored.ggmlv3.q8_0.bin'
main: error: unable to load model