mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
b3988621c5
# Add C Transformers for GGML Models I created Python bindings for the GGML models: https://github.com/marella/ctransformers Currently it supports GPT-2, GPT-J, GPT-NeoX, LLaMA, MPT, etc. See [Supported Models](https://github.com/marella/ctransformers#supported-models). It provides a unified interface for all models: ```python from langchain.llms import CTransformers llm = CTransformers(model='/path/to/ggml-gpt-2.bin', model_type='gpt2') print(llm('AI is going to')) ``` It can be used with models hosted on the Hugging Face Hub: ```py llm = CTransformers(model='marella/gpt-2-ggml') ``` It supports streaming: ```py from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler llm = CTransformers(model='marella/gpt-2-ggml', callbacks=[StreamingStdOutCallbackHandler()]) ``` Please see [README](https://github.com/marella/ctransformers#readme) for more details. --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
22 lines
617 B
Python
22 lines
617 B
Python
"""Test C Transformers wrapper."""
|
|
|
|
from langchain.llms import CTransformers
|
|
from tests.unit_tests.callbacks.fake_callback_handler import FakeCallbackHandler
|
|
|
|
|
|
def test_ctransformers_call() -> None:
|
|
"""Test valid call to C Transformers."""
|
|
config = {"max_new_tokens": 5}
|
|
callback_handler = FakeCallbackHandler()
|
|
|
|
llm = CTransformers(
|
|
model="marella/gpt-2-ggml",
|
|
config=config,
|
|
callbacks=[callback_handler],
|
|
)
|
|
|
|
output = llm("Say foo:")
|
|
assert isinstance(output, str)
|
|
assert len(output) > 1
|
|
assert 0 < callback_handler.llm_streams <= config["max_new_tokens"]
|