Llama-3.1-8B-ModelOpt-FP8

Llama-3.1-8B-Instruct Quantized (ModelOpt FP8)

This is a quantized version of meta-llama/Llama-3.1-8B-Instruct using modelopt with FP8 weight quantization.

Model Details

• Base Model: meta-llama/Llama-3.1-8B-Instruct
• Quantization Method: modelopt FP8 Post-Training Quantization (PTQ)
• Weight Precision: FP8
• Original Size: ~16 GB (bfloat16)
• Quantized Size: ~9 GB

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base model structure
model = AutoModelForCausalLM.from_pretrained(
    "tokenlabsdotrun/Llama-3.1-8B-ModelOpt-FP8",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True
)

# Load tokenizer and generate
tokenizer = AutoTokenizer.from_pretrained("tokenlabsdotrun/Llama-3.1-8B-ModelOpt-FP8")

inputs = tokenizer("Hello, my name is", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=10)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

License

This model inherits the Llama 3.1 Community License.