baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Update docstring

Browse source
This commit is contained in:
Andrei Betlen 2023-03-25 12:33:18 -04:00
parent 206efa39df
commit b121b7c05b
1 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
llama_cpp/llama.py
View file

@ -24,13 +24,13 @@ class Llama:
"""Load a llama.cpp model from `model_path`. """Load a llama.cpp model from `model_path`.
Args: Args:
model_path: Path to the model directory. model_path: Path to the model.
n_ctx: Number of tokens to keep in memory. n_ctx: Maximum context size.
n_parts: Number of parts to split the model into. If -1, the number of parts is automatically determined. n_parts: Number of parts to split the model into. If -1, the number of parts is automatically determined.
seed: Random seed. seed: Random seed. 0 for random.
f16_kv: Use half-precision for key/value matrices. f16_kv: Use half-precision for key/value cache.
logits_all: Return logits for all tokens, not just the vocabulary. logits_all: Return logits for all tokens, not just the last token.
vocab_only: Only use tokens in the vocabulary. vocab_only: Only load the vocabulary no weights.
n_threads: Number of threads to use. If None, the number of threads is automatically determined. n_threads: Number of threads to use. If None, the number of threads is automatically determined.
Raises: Raises: