Skip to content

convert to guff and ollama  #10

@Aniwine

Description

@Aniwine

I want to deploy it via ollama, so I firstly convert it to .guff file by llama.cpp's convert_hf_to_guff.py,but I got an error that KeyError "<|user|>",so I found it not in added_tokens_decoder of tokenizer_config.json while it exists in convert_hf_to_guff.py.So I comment this line out, code can finish normally.And ollama create model also successfully completed.But when ollama run model,I got tensor number errors,
image

I wonder what happens after removing the <|user|> keyword and how should I fix this?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions