File size: 1,203 Bytes
86442c0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
---
tags:
- fp8
language:
- en
base_model: Sao10K/Llama-3.1-8B-Stheno-v3.4
---
Original Model: https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4
Quantized with FP8 using https://github.com/neuralmagic/AutoFP8
Script:
```python
from datasets import load_dataset
from transformers import AutoTokenizer
from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
pretrained_model_dir = "Sao10K/Llama-3.1-8B-Stheno-v3.4"
quantized_model_dir = "Llama-3.1-8B-Stheno-v3.4-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",
ignore_patterns=["re:.*lm_head"],
)
model = AutoFP8ForCausalLM.from_pretrained(
pretrained_model_dir, quantize_config=quantize_config
)
model.quantize(examples)
model.save_quantized(quantized_model_dir)
``` |