diff --git a/extensions/xla/generate/adapter.py b/extensions/xla/generate/adapter.py index 097abe4e56..f6fb0920d3 100644 --- a/extensions/xla/generate/adapter.py +++ b/extensions/xla/generate/adapter.py @@ -29,7 +29,7 @@ def setup( adapter_path: Path = Path("out/adapter/alpaca/lit_model_adapter_finetuned.pth"), checkpoint_dir: Path = Path("checkpoints/tiiuae/falcon-7b"), max_new_tokens: int = 100, - top_k: Optional[int] = 200, + top_k: Optional[int] = 50, temperature: float = 0.8, precision: str = "bf16-true", ) -> None: diff --git a/litgpt/generate/adapter.py b/litgpt/generate/adapter.py index 104b3e20b0..91ebd18397 100644 --- a/litgpt/generate/adapter.py +++ b/litgpt/generate/adapter.py @@ -23,7 +23,7 @@ def main( checkpoint_dir: Path = Path("checkpoints/stabilityai/stablelm-base-alpha-3b"), quantize: Optional[Literal["bnb.nf4", "bnb.nf4-dq", "bnb.fp4", "bnb.fp4-dq", "bnb.int8"]] = None, max_new_tokens: int = 100, - top_k: Optional[int] = 200, + top_k: Optional[int] = 50, temperature: float = 0.8, precision: Optional[str] = None, ) -> None: diff --git a/litgpt/generate/adapter_v2.py b/litgpt/generate/adapter_v2.py index c7aeee8a91..0d25092135 100644 --- a/litgpt/generate/adapter_v2.py +++ b/litgpt/generate/adapter_v2.py @@ -23,7 +23,7 @@ def main( checkpoint_dir: Path = Path("checkpoints/stabilityai/stablelm-base-alpha-3b"), quantize: Optional[Literal["bnb.nf4", "bnb.nf4-dq", "bnb.fp4", "bnb.fp4-dq", "bnb.int8"]] = None, max_new_tokens: int = 100, - top_k: Optional[int] = 200, + top_k: Optional[int] = 50, temperature: float = 0.8, precision: Optional[str] = None, ) -> None: diff --git a/litgpt/generate/base.py b/litgpt/generate/base.py index 6488717429..060604b43f 100644 --- a/litgpt/generate/base.py +++ b/litgpt/generate/base.py @@ -96,7 +96,7 @@ def main( *, num_samples: int = 1, max_new_tokens: int = 50, - top_k: Optional[int] = 200, + top_k: Optional[int] = 50, temperature: float = 0.8, checkpoint_dir: Path = Path("checkpoints/stabilityai/stablelm-base-alpha-3b"), quantize: Optional[Literal["bnb.nf4", "bnb.nf4-dq", "bnb.fp4", "bnb.fp4-dq", "bnb.int8"]] = None, diff --git a/litgpt/generate/full.py b/litgpt/generate/full.py index 608115a5e1..c570e8dd2e 100644 --- a/litgpt/generate/full.py +++ b/litgpt/generate/full.py @@ -22,7 +22,7 @@ def main( checkpoint_dir: Path = Path("checkpoints/stabilityai/stablelm-base-alpha-3b"), quantize: Optional[Literal["bnb.nf4", "bnb.nf4-dq", "bnb.fp4", "bnb.fp4-dq", "bnb.int8"]] = None, max_new_tokens: int = 100, - top_k: Optional[int] = 200, + top_k: Optional[int] = 50, temperature: float = 0.8, precision: Optional[str] = None, ) -> None: diff --git a/litgpt/generate/sequentially.py b/litgpt/generate/sequentially.py index f804c4cffc..9f006ab47f 100644 --- a/litgpt/generate/sequentially.py +++ b/litgpt/generate/sequentially.py @@ -116,7 +116,7 @@ def main( *, num_samples: int = 1, max_new_tokens: int = 50, - top_k: Optional[int] = 200, + top_k: Optional[int] = 50, temperature: float = 0.8, checkpoint_dir: Path = Path("checkpoints/mistralai/Mistral-7B-Instruct-v0.1"), quantize: Optional[Literal["bnb.nf4", "bnb.nf4-dq", "bnb.fp4", "bnb.fp4-dq"]] = None, diff --git a/litgpt/generate/tp.py b/litgpt/generate/tp.py index 5c56dd1c09..41492f75b2 100644 --- a/litgpt/generate/tp.py +++ b/litgpt/generate/tp.py @@ -94,7 +94,7 @@ def main( *, num_samples: int = 1, max_new_tokens: int = 50, - top_k: Optional[int] = 200, + top_k: Optional[int] = 50, temperature: float = 0.8, checkpoint_dir: Path = Path("checkpoints/stabilityai/stablelm-base-alpha-3b"), quantize: Optional[Literal["bnb.nf4", "bnb.nf4-dq", "bnb.fp4", "bnb.fp4-dq"]] = None,