Suggerimenti per miglioramenti
#2
by
luigisaetta
- opened
If i can suggest a very small improvment in the code, since Mistral is perfectly supported by Transformers
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16, device_map="auto").eval()
instead of:
transformers.LlamaForCausalLMfrom_pretrained
Grazie del suggerimento. Lo abbiamo sistemato!!
Moxoff
changed discussion status to
closed