Instructions to use prdev/query-gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prdev/query-gen with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prdev/query-gen", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use prdev/query-gen 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 prdev/query-gen 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 prdev/query-gen to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for prdev/query-gen to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="prdev/query-gen", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -40,8 +40,7 @@ from unsloth import FastLanguageModel
|
|
| 40 |
from transformers import TextStreamer
|
| 41 |
|
| 42 |
# Load the finetuned model and tokenizer from Hugging Face Hub.
|
| 43 |
-
|
| 44 |
-
model, tokenizer = FastLanguageModel.from_pretrained("your_username/your_model_repo_name", load_in_4bit=True)
|
| 45 |
|
| 46 |
# Enable faster inference if supported.
|
| 47 |
FastLanguageModel.for_inference(model)
|
|
|
|
| 40 |
from transformers import TextStreamer
|
| 41 |
|
| 42 |
# Load the finetuned model and tokenizer from Hugging Face Hub.
|
| 43 |
+
model, tokenizer = FastLanguageModel.from_pretrained("prdev/query-gen", load_in_4bit=True)
|
|
|
|
| 44 |
|
| 45 |
# Enable faster inference if supported.
|
| 46 |
FastLanguageModel.for_inference(model)
|