update

README.md

@@ -48,19 +48,19 @@ model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", devic
 inputs = tokenizer(["The quick brown"], return_tensors="pt").to(model.device)
 
 # Basic sampling
-gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache", trust_remote_code=True)
+gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache_hf_helpers", trust_remote_code=True)
 
 # With temperature
-gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache", temperature=0.8, trust_remote_code=True)
+gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache_hf_helpers", temperature=0.8, trust_remote_code=True)
 
 # With top-k
-gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache", top_k=50, trust_remote_code=True)
+gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache_hf_helpers", top_k=50, trust_remote_code=True)
 
 # With top-p (nucleus sampling)
-gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache", top_p=0.9, trust_remote_code=True)
+gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache_hf_helpers", top_p=0.9, trust_remote_code=True)
 
 # Greedy decoding (no sampling)
-gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache", do_sample=False, trust_remote_code=True)
+gen_out = model.generate(**inputs, custom_generate="manueldeprada/sampling_with_kvcache_hf_helpers", do_sample=False, trust_remote_code=True)
 
 # Get detailed output with probabilities
 gen_out = model.generate(