Downloads · 30 days
7
18% of all-time downloads
Lemma-Mistral-7b-Adapter
marekk/Lemma-Mistral-7b-Adapter
Lemma-Mistral-7b-Adapter is a machine learning model from marekk. 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 peft.
All-time downloads
40
Public
Repo size
13.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.6 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Mar 12, 2024
- Updated
- Mar 12, 2024
- SHA
- 62660d20
Base models
Model card
From the Hugging Face model README
!pip install peft accelerate bitsandbytes
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer
adapater_path = "marekk/Lemma-Mistral-7b-Adapter"
config = PeftConfig.from_pretrained(adapater_path)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, load_in_4bit=True)
model = PeftModel.from_pretrained(model, adapater_path)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
from transformers import pipeline
generator = pipeline('text-generation', model = model, tokenizer=tokenizer)
generator('Render a list by altering each string to its basic lemma form of sport Teams, players and leagues. List:["Slavii", "Spartě", "Olomoucké"]', max_length = 100, num_return_sequences=1 , return_full_text=False, temperature=0.1)
Framework versions
- PEFT 0.8.2
- Library
- peft
- Created
- Mar 12, 2024
- Updated
- Mar 12, 2024