Downloads · 30 days
6
30% of all-time downloads
EleutherAI-polyglot-ko-5.8b-adapter
m2af/EleutherAI-polyglot-ko-5.8b-adapter
EleutherAI-polyglot-ko-5.8b-adapter is a text generation model from m2af. Use it when you need the model to write or continue text. It is set up for adapter-transformers. The card lists the license as apache-2.0.
Fine-tuned QLoRA Adapter for model EleutherAI/polyglot-ko-5.8b
All-time downloads
20
Public
Repo size
29.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29.4 MB · 100%
At a glance
- Task
- Text Generation
- Library
- adapter-transformers
- License
- apache-2.0
- Access
- Public
- Created
- Mar 25, 2024
- Updated
- Mar 26, 2024
- SHA
- 16b5249c
Model card
From the Hugging Face model README
Chat Model QLoRA Adapter
Fine-tuned QLoRA Adapter for model EleutherAI/polyglot-ko-5.8b
Fine-tuned with Korean Sympathy Conversation dataset from AIHub
See more informations at our GitHub
Datasets
Quick Tour
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"EleutherAI/polyglot-ko-5.8b",
low_cpu_mem_usage=True,
trust_remote_code=True,
device_map="auto",
)
model.config.use_cache = True
model.load_adapter("m2af/EleutherAI-polyglot-ko-5.8b-adapter", "loaded")
model.set_adapter("loaded")
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"
# Generate Sample
outputs = model.generate(**tokenizer("안녕하세요, 반갑습니다.", return_tensors="pt"))
print(outputs)
- Task
- Text Generation
- Library
- adapter-transformers
- License
- apache-2.0
- Languages
- ko
- Created
- Mar 25, 2024
- Updated
- Mar 26, 2024