18 lines
538 B
YAML
18 lines
538 B
YAML
name: qwen2
|
|
model: qwen2:7B
|
|
version: 1
|
|
|
|
# Results Preferences
|
|
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: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|