Downloads · 30 days
0
alpaca-native-7B-4bit-ggjt
LLukas22/alpaca-native-7B-4bit-ggjt
alpaca-native-7B-4bit-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 Sosaka/Alpaca-native-4bit-ggml with ggjt magic for use in llama.cpp or pyllamacpp. Full credit goes to Sosaka
Access
Public
Updated Apr 8, 2023
Repo size
4.2 GB
Likes
2
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 8, 2023
- SHA
- 84595218
Datasets
Model card
From the Hugging Face model README
Converted version of Sosaka/Alpaca-native-4bit-ggml with ggjt magic for use in llama.cpp or pyllamacpp. Full credit goes to Sosaka
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/alpaca-native-7B-4bit-ggjt", filename="ggjt-model.bin", local_dir=".")
#Load the model
model = Model(ggml_model="ggjt-model.bin", n_ctx=2000)
#Generate
prompt="The meaning of life is"
result=model.generate(prompt,n_predict=50)
- Languages
- en
- Created
- Apr 7, 2023
- Updated
- Apr 8, 2023