We introduce luxia-21.4b-alignment-v1.0, an instruction-tuned and alignment model based on luxia-21.4b.
Please refer to the evaluation results table for details.
We utilize state-of-the-art instruction fine-tuning methods including supervised fine-tuning (SFT) and direct preference optimization (DPO)
Results will be updated soon.
Results will be updated soon.
1# pip install transformers==4.35.2
2import torch
3from transformers import AutoModelForCausalLM, AutoTokenizer
4
5tokenizer = AutoTokenizer.from_pretrained("saltlux/luxia-21.4b-alignment-v0.1")
6model = AutoModelForCausalLM.from_pretrained(
7 "saltlux/luxia-21.4b-alignment-v0.1",
8 device_map="auto",
9 torch_dtype=torch.float16,
10)
Any questions and suggestions are welcomed at the discussion tab.
