MWeste's picture
Upload quantized Qwen model
def7743 verified
|
raw
history blame
1.08 kB
metadata
language:
  - en
  - zh
base_model: Qwen/Qwen3-0.6B-Base
tags:
  - quantized
  - qwen
  - causal-lm
license: apache-2.0

Quantized Qwen/Qwen3-0.6B-Base

This is a quantized version of Qwen/Qwen3-0.6B-Base.

Model Details

  • Base Model: Qwen/Qwen3-0.6B-Base
  • Model Type: Quantized Causal Language Model
  • Language(s): English, Chinese
  • License: Apache 2.0

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("your-username/your-repo-name")
model = AutoModelForCausalLM.from_pretrained("your-username/your-repo-name")

# Generate text
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_length=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

This model has been quantized to reduce memory usage while maintaining performance.

Ethical Considerations

Please refer to the original model's documentation for ethical considerations and limitations.