github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-17 23:41:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Breaking] Migrate GPT4All to use PyGPT4All (#3934)

Browse Source 
Seems the pyllamacpp package is no longer the supported bindings from
gpt4all. Tested that this works locally.

Given that the older models weren't very performant, I think it's better
to migrate now without trying to include a lot of try / except blocks

---------

Co-authored-by: Nissan Pow <npow@users.noreply.github.com>
Co-authored-by: Nissan Pow <pownissa@amazon.com>
This commit is contained in:
Zander Chase
2023-05-01 20:42:45 -07:00
committed by GitHub
parent f0a4bbb8e2
commit c4cb55a0c5
3 changed files with 178 additions and 187 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
tests/integration_tests/llms/test_gpt4all.py
View File

@@ -7,21 +7,12 @@ from langchain.llms import GPT4All
def _download_model() -> str:
"""Download model.
From https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized.bin,
convert to new ggml format and return model path."""
model_url = "https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized.bin"
tokenizer_url = "https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer.model"
conversion_script = "https://github.com/nomic-ai/pyllamacpp/blob/main/pyllamacpp/scripts/convert_gpt4all.py"
"""Download model."""
model_url = "http://gpt4all.io/models/ggml-gpt4all-l13b-snoozy.bin"
local_filename = model_url.split("/")[-1]
if not os.path.exists("convert_gpt4all.py"):
urlretrieve(conversion_script, "convert_gpt4all.py")
if not os.path.exists("tokenizer.model"):
urlretrieve(tokenizer_url, "tokenizer.model")
if not os.path.exists(local_filename):
urlretrieve(model_url, local_filename)
os.system(f"python convert_gpt4all.py.py . tokenizer.model")
return local_filename