Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add LoRA loading for the LlamaCpp LLM #3363

Merged
merged 3 commits into from
Apr 25, 2023
Merged

add LoRA loading for the LlamaCpp LLM #3363

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7d99b4d
add LoRA loading for the llamacpp LLM
horenbergerb Apr 22, 2023
428f8dc
remove logic to disable mmap when lora is used
horenbergerb Apr 23, 2023
df215dd
Merge branch 'master' into add-lora-loading-to-llamacpp
horenbergerb Apr 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions langchain/llms/llamacpp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,12 @@ class LlamaCpp(LLM):
model_path: str
"""The path to the Llama model file."""

lora_base: Optional[str] = None
"""The path to the Llama LoRA base model."""

lora_path: Optional[str] = None
"""The path to the Llama LoRA. If None, no LoRa is loaded."""

n_ctx: int = Field(512, alias="n_ctx")
"""Token context window."""

Expand Down Expand Up @@ -87,13 +93,18 @@ class LlamaCpp(LLM):
last_n_tokens_size: Optional[int] = 64
"""The number of tokens to look back when applying the repeat_penalty."""

use_mmap: Optional[bool] = True
"""Whether to keep the model loaded in RAM"""

streaming: bool = True
"""Whether to stream the results, token by token."""

@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that llama-cpp-python library is installed."""
model_path = values["model_path"]
lora_path = values["lora_path"]
lora_base = values["lora_base"]
n_ctx = values["n_ctx"]
n_parts = values["n_parts"]
seed = values["seed"]
Expand All @@ -103,13 +114,16 @@ def validate_environment(cls, values: Dict) -> Dict:
use_mlock = values["use_mlock"]
n_threads = values["n_threads"]
n_batch = values["n_batch"]
use_mmap = values["use_mmap"]
last_n_tokens_size = values["last_n_tokens_size"]

try:
from llama_cpp import Llama

values["client"] = Llama(
model_path=model_path,
lora_base=lora_base,
lora_path=lora_path,
n_ctx=n_ctx,
n_parts=n_parts,
seed=seed,
Expand All @@ -119,6 +133,7 @@ def validate_environment(cls, values: Dict) -> Dict:
use_mlock=use_mlock,
n_threads=n_threads,
n_batch=n_batch,
use_mmap=use_mmap,
last_n_tokens_size=last_n_tokens_size,
)
except ImportError:
Expand Down