Downloads · 30 days
0
alpaca-lora-7b-german-base-52k
avocardio/alpaca-lora-7b-german-base-52k
alpaca-lora-7b-german-base-52k is a machine learning model from avocardio. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Visit the Github for more information: https://github.com/avocardio/zicklein
Access
Public
Updated May 22, 2023
Repo size
16.8 MB
Likes
14
Public
Repo makeup
Click a slice to open those files.
.bin16.8 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- May 20, 2023
- Updated
- May 22, 2023
- SHA
- ef88b4ed
Model card
From the Hugging Face model README
Zicklein: german 🇩🇪 finetuned instruction LLaMA
Visit the Github for more information: https://github.com/avocardio/zicklein
Usage
from peft import PeftModel
from transformers import LLaMATokenizer, LLaMAForCausalLM, GenerationConfig
tokenizer = LLaMATokenizer.from_pretrained("decapoda-research/llama-7b-hf")
model = LLaMAForCausalLM.from_pretrained(
"decapoda-research/llama-7b-hf",
load_in_8bit=False,
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(model, "avocardio/alpaca-lora-7b-german-base-52k")
- Library
- transformers
- License
- apache-2.0
- Languages
- de
- Created
- May 20, 2023
- Updated
- May 22, 2023