translator-llm / Modelfile
johnpaulbin's picture
Create Modelfile
9480b0b verified
raw
history blame contribute delete
285 Bytes
FROM translator-llama3.1-q4km.gguf
# sets the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 0.1
# sets the context window size to 2000, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 2000