name: tinyllama 1B
model: tinyllama:1B
version: 1

# Results Preferences
stop:
  - </s>
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: "\n\n<|system|>\n{system_message}</s>\n\n\n\n\n<|user|>\n{prompt}</s>\n\n\n<|assistant|>\n\n"