initial commit

initial comit

Fix env

.gitignore

@@ -0,0 +1 @@
+.env 

README.md

@@ -1,5 +1,5 @@
 ---
-title: Gradio Chatbot
+title: Renj Portfolio Ai Bot
 emoji: 💬
 colorFrom: yellow
 colorTo: purple
@@ -7,6 +7,7 @@ sdk: gradio
 sdk_version: 5.0.1
 app_file: app.py
 pinned: false
+short_description: Me as assistant to me
 ---
 
 An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,45 +1,47 @@
+import os
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+# Load your model and tokenizer
+model_name = "Renjith95/renj-portfolio-finetuned-model"  # Replace with your model name
+auth_token = os.getenv("HF_TOKEN")  # Get token from environment variable
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=auth_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, use_auth_token=auth_token)
+
 
 """
 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("HuggingFaceH4/zephyr-7b-beta")
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, 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]})
-
+    for user_msg, assistant_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": assistant_msg})
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
+    inputs = tokenizer.apply_chat_template(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_tensors="pt"
+    ).to(model.device)
+
+    outputs = model.generate(
+        input_ids=inputs,
+        max_new_tokens=max_tokens,
+        use_cache=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
+    )
+    response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+    
+    # Assuming your model's response is the last part after the user's message
+    response = response.split(message)[-1].strip()  
+    yield response
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """

requirements.txt

@@ -1 +1,5 @@
-huggingface_hub==0.25.2
+gradio>=4.0.0
+huggingface_hub>=0.20.0
+transformers>=4.36.0
+torch>=2.0.0
+python-dotenv>=0.19.0