| # Ollama build file for the released chat model. Build the GGUF first: | |
| # python simple/export_gguf.py --run RUN --tokenizer PREP/tokenizer/tokenizer.json --out ovl-23m-chat-F32.gguf | |
| # ollama create openverifiablellm -f simple/Modelfile | |
| # Run `ollama create` from the directory that holds ovl-23m-chat-F32.gguf, or edit the FROM path. | |
| FROM ./ovl-23m-chat-F32.gguf | |
| # The training format: <|user|> text <|eos|> <|assistant|> text <|eos|> ... | |
| TEMPLATE """{{- range .Messages }}{{ if eq .Role "user" }}<|user|>{{ .Content }}<|eos|>{{ else if eq .Role "assistant" }}<|assistant|>{{ .Content }}<|eos|>{{ end }}{{ end }}<|assistant|>""" | |
| PARAMETER stop "<|eos|>" | |
| PARAMETER stop "<|user|>" | |
| PARAMETER num_ctx 512 | |
| PARAMETER temperature 0.8 | |