File size: 528 Bytes
f503cbc 1e8ea36 f503cbc 2a4bec0 f503cbc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
name: gemma
model: gemma:7B
version: 1
# Results Preferences
stop:
- <end_of_turn>
- <eos>
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_turn>user\n{prompt}<end_of_turn>\n<start_of_turn>model" |