ollama 无法导入DarkIdol-Llama-3.1-Instruct-1.2-Uncensored:8b_Q8_0

up9lanfz  于 6个月前  发布在  其他
关注(0)|答案(1)|浏览(100)

问题:

  1. modelfile
    FROM ./DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q8_0.gguf
    TEMPLATE "{{- if .Messages }}
    {{- if .System }}<|start_header_id|>system<|end_header_id|>
    {{ .System }}<|eot_id|>
    {{- end }}
    {{- range .Messages }}<|start_header_id|>{{ .Role }}<|end_header_id|>
    {{ .Content }}<|eot_id|>
    {{- end }}<|start_header_id|>assistant<|end_header_id|>
    {{ else }}
    {{- if .System }}<|start_header_id|>system<|end_header_id|>
    {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
    {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
    {{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}"
    PARAMETER stop <|start_header_id|>
    PARAMETER stop <|end_header_id|>
    PARAMETER stop <|eot_id|>
    taozhiyu@603e5f4a42f1 DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF % ollama create taozhiyuai/DarkIdol-Llama-3.1-Instruct-1.2-Uncensored:8b_Q8_0 -f modelfile
    transferring model data
    using existing layer sha256:9ad16d0a1bb54a5efcaa4dfbfde70254768724ec5f453934de4e688dca2a3070
    using existing layer sha256:cdbcae7e69d520e3d5a17b4979c31331dfba959f36641a81576349875d682127
    using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb
    creating new layer sha256:a67d6d41b0d6ca312152b392a024900ae436f3eee547dd5c914dadba0229bf8b
    writing manifest
    success
    taozhiyu@603e5f4a42f1 DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF % ollama run taozhiyuai/DarkIdol-Llama-3.1-Instruct-1.2-Uncensored:8b_Q8_0
    Error: llama runner process has terminated: error:done_getting_tensors: wrong number of tensors; expected 292, got 291

相关问题