how to avoid online downing while i have got the offline wight files

[arctanbell]

I want to] use the llm.llama2, but downloading files named like

so I downloaded the files llama-2-7b-chat.ggmlv3.q4_0 and llama-2-7b-chat.ggmlv3.q4_1 and placed them at the same dir, however the download still continued

[junjiejiangjjj]

You can also use the local path of a model file, which can be ran by llama-cpp-python.

chat = ops.LLM.Llama_2({YOUR_LOCAL_FILE_PATH}, n_ctx=4096, max_tokens=200)

[arctanbell]

i have try like this,

p = (
pipe.input('question', 'docs', 'history')
.map(('question', 'docs', 'history'), 'prompt', ops.prompt.question_answer())
.map('prompt', 'answer', ops.LLM.Llama_2('./llama-2-7b-chat.ggmlv3.q4_0.bin',n_ctx=4096, max_tokens=200))
.output('answer')
)
get the erro like:

gguf_init_from_file: invalid magic number 67676a74
error loading model: llama_model_loader: failed to load model from ./llama-2-7b-chat.ggmlv3.q4_0.bin
llama_load_model_from_file: failed to load model
i search this erro,get this answer https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/discussions/14, but have to change the version of llama.cpp,how to solver it ?

[junjiejiangjjj]

Install the previous version before this one: ggerganov/llama.cpp@dadbed9