|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
base_model: |
|
- Qwen/Qwen2.5-0.5B-Instruct |
|
new_version: ShubhaLabs/quantized_qwen_model |
|
--- |
|
# Quantized Qwen Model |
|
|
|
This repository contains a quantized version of the Qwen model for causal language modeling. |
|
|
|
## Model Details |
|
- **Model Type**: Qwen2ForCausalLM |
|
- **Quantization**: Dynamic Quantization |
|
|
|
## Usage |
|
You can load this model using the Hugging Face Transformers library: |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model = AutoModelForCausalLM.from_pretrained("ShubhaLabs/quantized_qwen_model") |
|
tokenizer = AutoTokenizer.from_pretrained("ShubhaLabs/quantized_qwen_model") |
