Instructions to use iknow-lab/0725-ko-genstruct-v0.2-simple-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use iknow-lab/0725-ko-genstruct-v0.2-simple-qa with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("MLP-KTLim/llama-3-Korean-Bllossom-8B") model = PeftModel.from_pretrained(base_model, "iknow-lab/0725-ko-genstruct-v0.2-simple-qa") - Transformers
How to use iknow-lab/0725-ko-genstruct-v0.2-simple-qa with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("iknow-lab/0725-ko-genstruct-v0.2-simple-qa", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use iknow-lab/0725-ko-genstruct-v0.2-simple-qa with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for iknow-lab/0725-ko-genstruct-v0.2-simple-qa to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for iknow-lab/0725-ko-genstruct-v0.2-simple-qa to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for iknow-lab/0725-ko-genstruct-v0.2-simple-qa to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="iknow-lab/0725-ko-genstruct-v0.2-simple-qa", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,7 @@ tags:
|
|
| 11 |
- trl
|
| 12 |
datasets:
|
| 13 |
- lcw99/wikipedia-korean-20240501-1million-qna
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<img src="https://huggingface.co/iknow-lab/ko-genstruct-v0.1/resolve/main/image.webp" />
|
|
|
|
| 11 |
- trl
|
| 12 |
datasets:
|
| 13 |
- lcw99/wikipedia-korean-20240501-1million-qna
|
| 14 |
+
library_name: peft
|
| 15 |
---
|
| 16 |
|
| 17 |
<img src="https://huggingface.co/iknow-lab/ko-genstruct-v0.1/resolve/main/image.webp" />
|