docs: Add Llama class example

This commit is contained in:
Andrei Betlen 2023-11-22 23:10:04 -05:00
parent c5173b0fb3
commit b6bb7ac76a

View file

@ -766,6 +766,30 @@ class Llama:
):
"""Load a llama.cpp model from `model_path`.
Examples:
Basic usage
>>> import llama_cpp
>>> model = llama_cpp.Llama(
... model_path="path/to/model",
... )
>>> print(model("The quick brown fox jumps ", stop=["."])["choices"][0]["text"])
the lazy dog
Loading a chat model
>>> import llama_cpp
>>> model = llama_cpp.Llama(
... model_path="path/to/model",
... chat_format="llama-2",
... )
>>> print(model.create_chat_completion(
... messages=[{
... "role": "user",
... "content": "what is the meaning of life?"
... }]
... ))
Args:
model_path: Path to the model.
n_gpu_layers: Number of layers to offload to GPU (-ngl). If -1, all layers are offloaded.