Snow.Zeng

icon company UESTC icon location Chengdu icon location A boy loving computer sience &footbal&movie&books Interests:Smart Network&Federated Learing&Distributed ML&Security

Results 1 issues of Snow.Zeng

What if I want to use decoder only model?

In your evaluate_llm.py, you wrote: `opts = parser.parse_args() model = AutoModelForSeq2SeqLM.from_pretrained(opts.model_addr, cache_dir=opts.cache_dir) tokenizer = AutoTokenizer.from_pretrained(opts.model_addr, cache_dir=opts.cache_dir) collator = DataCollatorForSeq2Seq(tokenizer = tokenizer, model = model, max_length = opts.max_length)` But what if...