model.yml

name: granite
model: granite:8B
version: 1

# Results Preferences
stop:
  - </s>
  - <|end_of_text|>
  - <|end_of_role|>
top_p: 0.95
temperature: 0.7
frequency_penalty: 0
presence_penalty: 0
max_tokens: 4096 # Infer from base config.json -> max_position_embeddings
stream: true # true | false

# Engine / Model Settings
ngl: 33 # Infer from base config.json -> num_attention_heads
ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
engine: llama-cpp
prompt_template: "<|start_of_role|>system<|end_of_role|>{system_message}<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>"