Update README.md

README.md

@@ -139,7 +139,7 @@ Use the code below to get started with the model. You can run conversational inf
 import transformers
 import torch
 
-model_id = "HPAI-BSC/Qwen2.5-Aloe-Beta-7B"
+model_id = "HPAI-BSC/Qwen2.5-Aloe-Beta-72B"
 
 pipeline = transformers.pipeline(
     "text-generation",
@@ -161,7 +161,7 @@ prompt = pipeline.tokenizer.apply_chat_template(
 
 terminators = [
     pipeline.tokenizer.eos_token_id,
-    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+    pipeline.tokenizer.convert_tokens_to_ids("<|im_end|>")
 ]
 
 outputs = pipeline(
@@ -169,8 +169,10 @@ outputs = pipeline(
     max_new_tokens=256,
     eos_token_id=terminators,
     do_sample=True,
-    temperature=0.6,
-    top_p=0.9,
+    temperature=0.7,
+    top_p=0.8,
+    top_k=20,
+    repetition_penalty=1.05
 )
 print(outputs[0]["generated_text"][len(prompt):])
 ```
@@ -181,7 +183,7 @@ print(outputs[0]["generated_text"][len(prompt):])
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "HPAI-BSC/Qwen2.5-Aloe-Beta-7B"
+model_id = "HPAI-BSC/Qwen2.5-Aloe-Beta-72B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
@@ -203,7 +205,7 @@ input_ids = tokenizer.apply_chat_template(
 
 terminators = [
     tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+    tokenizer.convert_tokens_to_ids("<|im_end|>")
 ]
 
 outputs = model.generate(
@@ -211,8 +213,10 @@ outputs = model.generate(
     max_new_tokens=256,
     eos_token_id=terminators,
     do_sample=True,
-    temperature=0.6,
-    top_p=0.9,
+    temperature=0.7,
+    top_p=0.8,
+    top_k=20,
+    repetition_penalty=1.05
 )
 response = outputs[0][input_ids.shape[-1]:]
 print(tokenizer.decode(response, skip_special_tokens=True))