test with google/flan-t5-small

app.py

@@ -1,20 +1,9 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-#client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")
-#client = InferenceClient("microsoft/MAI-DS-R1") ERROR
-#client = InferenceClient("meta-llama/Llama-3.1-8B-Instruct") ERROR
-#client = InferenceClient("nvidia/Nemotron-H-47B-Base-8K") ERROR
-#client = InferenceClient("meta-llama/Llama-3.2-1B") TIMES OUT
-#client = InferenceClient("CohereLabs/c4ai-command-a-03-2025") ERROR
-#client = InferenceClient("meta-llama/Llama-3.2-3B-Instruct") TIMES OUT 
-#client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct") TIMES OUT
-client = InferenceClient(model="prompthero/openjourney-v4")
+from transformers import T5Tokenizer, T5ForConditionalGeneration
 
+# Initialize the T5 model and tokenizer
+tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
+model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small")
 
 def respond(
     message,
@@ -35,20 +24,18 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    # Create a prompt for the T5 model
+    prompt = "translate English to Italian: "
+    for message in messages:
+        prompt += message["content"] + " "
+    prompt = prompt.strip()
 
-        response += token
-        yield response
+    # Generate a response using the T5 model
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+    outputs = model.generate(input_ids, max_length=max_tokens, temperature=temperature, top_p=top_p)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
+    return response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface