Update README.md

README.md

@@ -5,7 +5,7 @@ datasets:
 - uonlp/CulturaX
 - pg19
 - bigcode/starcoderdata
-- manu/croissant_dataset
+- croissantllm/croissant_dataset
 language:
 - fr
 - en
@@ -65,7 +65,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
 
 inputs = tokenizer("I am so tired I could sleep right now. -> Je suis si fatigué que je pourrais m'endormir maintenant.\nHe is heading to the market. -> Il va au marché.\nWe are running on the beach. ->", return_tensors="pt").to(model.device)
-tokens = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=60, temperature=0.5)
+tokens = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=60, temperature=0.3)
 print(tokenizer.decode(tokens[0]))
 
 # remove bos token