|
--- |
|
tags: |
|
- fp8 |
|
- vllm |
|
--- |
|
|
|
See original model card for information about how it was made. This is to enable fast inference use with Hopper level hardware in FP8. I quantized it to FP8 using neuralmagic code below on 4x L40s. |
|
|
|
https://huggingface.co/alpindale/magnum-72b-v1 |
|
|
|
# Magnum-72b-v1-FP8 |
|
|
|
## Model Overview |
|
* <h3 style="display: inline;">Model Architecture:</h3> Based on and identical to the Qwen2-72B-Instruct architecture |
|
* <h3 style="display: inline;">Model Optimizations:</h3> Weights and activations quantized to FP8 |
|
* <h3 style="display: inline;">Release Date:</h3> June 25, 2024 |
|
|
|
Magnum-72B-v1 quantized to FP8 weights and activations using per-tensor quantization through the [AutoFP8 repository](https://github.com/neuralmagic/AutoFP8), ready for inference with vLLM >= 0.5.0. |
|
Calibrated with 512 UltraChat samples to achieve better performance recovery. |
|
Part of the [FP8 LLMs for vLLM collection](https://huggingface.co/collections/neuralmagic/fp8-llms-for-vllm-666742ed2b78b7ac8df13127). |
|
|
|
## Usage and Creation |
|
Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py). |
|
|
|
```python |
|
from datasets import load_dataset |
|
from transformers import AutoTokenizer |
|
|
|
from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig |
|
|
|
pretrained_model_dir = "alpindale/magnum-72b-v1" |
|
quantized_model_dir = "Magnum-72B-FP8" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True, model_max_length=4096) |
|
tokenizer.pad_token = tokenizer.eos_token |
|
|
|
ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512)) |
|
examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds] |
|
examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda") |
|
|
|
quantize_config = BaseQuantizeConfig(quant_method="fp8", activation_scheme="static") |
|
|
|
model = AutoFP8ForCausalLM.from_pretrained( |
|
pretrained_model_dir, quantize_config=quantize_config |
|
) |
|
model.quantize(examples) |
|
model.save_quantized(quantized_model_dir) |
|
``` |
