Instructions to use vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1 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 vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1 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 vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="vietphuon/Llama-3.2-1B-Instruct-bnb-4bit-240926-1", max_seq_length=2048, )
Update README.md
Browse filesUpdate description
README.md
CHANGED
|
@@ -12,6 +12,9 @@ tags:
|
|
| 12 |
datasets:
|
| 13 |
- yahma/alpaca-cleaned
|
| 14 |
---
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
# Uploaded model
|
| 17 |
|
|
|
|
| 12 |
datasets:
|
| 13 |
- yahma/alpaca-cleaned
|
| 14 |
---
|
| 15 |
+
# Description
|
| 16 |
+
|
| 17 |
+
- **Motivation:** Fine-tuned version of Llama 3.2 model to generate a quiz for a given context. This version is just poorly trained on the Alpaca version (Chatbot usecase). Also this dataset only have 38 data points on json task so the model also weak on structured json output.
|
| 18 |
|
| 19 |
# Uploaded model
|
| 20 |
|