Downloads · 30 days
0
gpt4all-lora-quantized-ggjt
LLukas22/gpt4all-lora-quantized-ggjt
gpt4all-lora-quantized-ggjt is a machine learning model from LLukas22. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Converted version of gpt4all weights with ggjt magic for use in llama.cpp or pyllamacpp. Full credit goes to the GPT4All project.
Access
Public
Updated Apr 7, 2023
Repo size
4.2 GB
Likes
32
Public
Repo makeup
Click a slice to open those files.
.bin4.2 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 7, 2023
- Updated
- Apr 7, 2023
- SHA
- 2e7367a8
Model card
From the Hugging Face model README
Converted version of gpt4all weights with ggjt magic for use in llama.cpp or pyllamacpp. Full credit goes to the GPT4All project.
Usage via pyllamacpp
Installation: pip install pyllamacpp
Download and inference:
from huggingface_hub import hf_hub_download
from pyllamacpp.model import Model
#Download the model
hf_hub_download(repo_id="LLukas22/gpt4all-lora-quantized-ggjt", filename="ggjt-model.bin", local_dir=".")
#Load the model
model = Model(ggml_model="ggjt-model.bin", n_ctx=2000)
#Generate
prompt="User: How are you doing?\nBot:"
result=model.generate(prompt,n_predict=50)
- Languages
- en
- Created
- Apr 7, 2023
- Updated
- Apr 7, 2023