Update README.md

README.md

@@ -24,8 +24,11 @@ ELlama1-0.7b - pretrain модель, обученная на семпле из
 import torch
 from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast
 
+device = "cuda"
+
 model_path = "dmitry315/ELlama1-0.7b"
 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.float16, trust_remote_code=True)
+model.to(device)
 tokenizer = PreTrainedTokenizerFast.from_pretrained(model_path, trust_remote_code=True)
 
 text = "Γεια σας , δεν ξερω τιποτα για τον Ηροδοτο , μπορειτε να μου πειτε γι ' αυτον ;"
@@ -41,8 +44,8 @@ with torch.no_grad():
     outputs = model.generate(
         inputs.input_ids,
         max_length=128,
-        temperature=args.temperature,
-        top_p=args.top_p,
+        temperature=1.0,
+        top_p=50,
         do_sample=True,
         pad_token_id=tokenizer.eos_token_id,
         num_return_sequences=1