add: model

app.py

@@ -1,10 +1,20 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+# Load model and tokenizer
+model_name = "martinbravo/llama_finetuned_test"
+base_model_name = "unsloth/llama-3.2-1b-instruct-bnb-4bit"
+
+# Load tokenizer and model locally
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",  # Automatically maps model to GPU/CPU
+    trust_remote_code=True,  # If model uses custom implementations
+)
 
-"""
-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("martinbravo/llama_finetuned_test")
+# Create a text-generation pipeline
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
 
 
 def respond(
@@ -15,34 +25,27 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Build input prompt
+    prompt = system_message + "\n"
+    for user_input, assistant_response in history:
+        prompt += f"User: {user_input}\nAssistant: {assistant_response}\n"
+    prompt += f"User: {message}\nAssistant:"
+
+    # Generate response
+    response = generator(
+        prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True,  # Sampling for diverse responses
+    )[0]["generated_text"]
 
-        response += token
-        yield response
+    # Extract the assistant's response
+    assistant_response = response[len(prompt) :].strip()
+    yield assistant_response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -51,14 +54,10 @@ demo = gr.ChatInterface(
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
+            maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"
         ),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio
+transformers

test.py

@@ -0,0 +1,16 @@
+from transformers import AutoModel, AutoTokenizer
+
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained("martinbravo/llama_finetuned_test")
+
+# Load the model
+model = AutoModel.from_pretrained("martinbravo/llama_finetuned_test")
+
+# Test the model
+input_text = "What is the capital of France?"
+inputs = tokenizer(input_text, return_tensors="pt")
+
+# Perform inference
+outputs = model(**inputs)
+
+print(outputs)