CoolFace
Modelpublic

ModelCloud/Llama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v1

sourceHugging Facellama3.2updated 2y agoView on Hugging Face
2likes162downloads
Model Card

image/png

This model has been quantized using GPTQModel.

  • —bits: 4
  • —dynamic: null
  • —group_size: 32
  • —desc_act: true
  • —static_groups: false
  • —sym: true
  • —lm_head: false
  • —true_sequential: true
  • —quant_method: "gptq"
  • —checkpoint_format: "gptq"
  • —meta：
  • —quantizer: gptqmodel:1.1.0
  • —uri: https://github.com/modelcloud/gptqmodel
  • —damp_percent: 0.1
  • —damp_auto_increment: 0.0015

Example:

python
from transformers import AutoTokenizer
from gptqmodel import GPTQModel

model_name = "ModelCloud/Llama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v1"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = GPTQModel.from_quantized(model_name)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=512)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)

print(result)