Ollama run failed

[hunger09]

inspur@inspur-gpuserver:~$ ollama run openbmb/minicpm-v4.6:latest
Error: 500 Internal Server Error: unable to load model: /data/ollama/models/blobs/sha256-6b0c74962c44bc6bf4b655b9b02c13eda9d5a0491543ae976d1ac18e4b7892e2

both Win and linux got the same error.

Then I downloaded the gguf from modelscope. Following the doc got another error.

inspur@inspur-gpuserver:/data/modelscope/models/MiniCPM-v46-gguf$ cat minicpmv4.6.Modelfile
FROM /data/modelscope/models/MiniCPM-v46-gguf/MiniCPM-V-4.6-Q4_K_M.gguf
FROM /data/modelscope/models/MiniCPM-v46-gguf/mmproj-MiniCPM-V-4.6-F16.gguf

TEMPLATE """{{- if .Messages }}{{- range $i, $_ := .Messages }}{{- $last := eq (len (slice $.Messages $i)) 1 -}}<|im_start|>{{ .Role }}{{ .Content }}{{- if $last }}{{- if (ne .Role "assistant") }}<|im_end|><|im_start|>assistant{{ end }}{{- else }}<|im_end|>{{ end }}{{- end }}{{- else }}{{- if .System }}<|im_start|>system{{ .System }}<|im_end|>{{ end }}{{ if .Prompt }}<|im_start|>user{{ .Prompt }}<|im_end|>{{ end }}<|im_start|>assistant{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""

SYSTEM """You are a helpful assistant."""

PARAMETER top_p 0.8
PARAMETER num_ctx 8192
PARAMETER stop ["<|im_start|>", "<|im_end|>"]
PARAMETER temperature 0.7

inspur@inspur-gpuserver:/data/modelscope/models/MiniCPM-v46-gguf$ ollama -v
ollama version is 0.23.2
inspur@inspur-gpuserver:/data/modelscope/models/MiniCPM-v46-gguf$ ollama create minicpmv -f minicpmv4.6.Modelfile
gathering model components
Error: 400 Bad Request: invalid model name

[tc-mb]

Hi, MiniCPM-V 4.6 requires Ollama 0.30 or newer. Please upgrade Ollama to the latest version, then pull from the official OpenBMB Ollama repo: https://ollama.com/openbmb/minicpm-v4.6

ollama run openbmb/minicpm-v4.6
Older Ollama releases don't include the model support and will fail to load.