Update app.py

app.py

@@ -1,14 +1,36 @@
-from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import gradio as gr
 
-model_id = "mistralai/Mistral-7B-Instruct-v0.2"
-tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+model_id = "teknium/OpenHermes-2.5-Mistral-7B"
 
-def generate_response(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    outputs = model.generate(**inputs, max_new_tokens=150, do_sample=True, temperature=0.7)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+# Carga el modelo y tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.float16,
+)
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.7,
+)
+
+# Interfaz Gradio
+def generate_text(prompt):
+    output = pipe(prompt)[0]["generated_text"]
+    return output
+
+gr.Interface(
+    fn=generate_text,
+    inputs=gr.Textbox(label="prompt"),
+    outputs=gr.Textbox(label="output"),
+    title="Amside AI",
+    theme="soft",
+).launch()
 
-import gradio as gr
-gr.Interface(fn=generate_response, inputs="text", outputs="text").launch()