Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,4 @@
+
 ---
 license: mit
 datasets:
@@ -53,10 +54,9 @@ model_name = "croissantllm/base_185k"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
 
-print(f"Number of parameters: {model.num_parameters()}")
-print(f"Number of non-embedding parameters: {model.num_parameters(exclude_embeddings=True)}")
-
-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)
+inputs = tokenizer("I am so tired I could sleep right now. -> Je suis si fatigué que je pourrais m'endormir maintenant.
+He is heading to the market. -> Il va au marché.
+We 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)
 print(tokenizer.decode(tokens[0]))
 
@@ -64,4 +64,4 @@ print(tokenizer.decode(tokens[0]))
 inputs = tokenizer("Capitales: France -> Paris, Italie -> Rome, Allemagne -> Berlin, Espagne ->", return_tensors="pt", add_special_tokens=True).to(model.device)
 tokens = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=60)
 print(tokenizer.decode(tokens[0]))
-```
+```