Upload folder using huggingface_hub

fined-tuned.lora.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f50855153040325fe2a203e7ee03c3aa8c98f3f3db7cccc435fa759527bd7b5
+size 5560280

main.py

@@ -1,32 +1,60 @@
-from openai import OpenAI
 import gradio as gr
-from dotenv import load_dotenv
+import os
+import keras_nlp
+from transformers import AutoModelForCausalLM
 
-load_dotenv()
 
-client = OpenAI()
+# Set Kaggle API credentials
 
+os.environ["KAGGLE_USERNAME"] = "rogerkorantenng"
+os.environ["KAGGLE_KEY"] = "9a33b6e88bcb6058b1281d777fa6808d"
 
-def generate_response(message, history):
-    formatted_history = []
-    for user, assistant in history:
-        formatted_history.append({"role": "user", "content": user})
-        formatted_history.append({"role": "assistant", "content": assistant})
-
-    formatted_history.append({"role": "user", "content": message})
-
-    response = client.chat.completions.create(model='gpt-3.5-turbo',
-                                              messages=formatted_history,
-                                              temperature=1.0)
+# Load LoRA weights if you have them
+LoRA_weights_path = "fined-tuned.lora.h5"
+gemma_lm = keras_nlp.models.GemmaCausalLM.from_preset("gemma_2b_en")
 
-    return response.choices[0].message.content
+gemma_lm.backbone.enable_lora(rank=4)  # Enable LoRA with rank 4
+gemma_lm.preprocessor.sequence_length = 512  # Limit sequence length
+gemma_lm.backbone.load_lora_weights(LoRA_weights_path)  # Load LoRA weights
 
-
-gr.ChatInterface(generate_response,
-                 chatbot=gr.Chatbot(height=300),
-                 textbox=gr.Textbox(placeholder="You can ask me anything", container=False, scale=7),
-                 title="OpenAI Chat Bot",
-                 retry_btn=None,
-                 undo_btn="Delete Previous",
-                 clear_btn="Clear").launch(share=True)
-gr.ChatInterface(generate_response).launch()
+# Define the response generation function
+def generate_response(message, history):
+    # Create a prompt template
+    template = "Instruction:\n{instruction}\n\nResponse:\n{response}"
+
+    # Format the history and the current message into the prompt
+    formatted_history = ""
+    for user_msg, bot_msg in history:
+        formatted_history += template.format(instruction=user_msg, response=bot_msg)
+
+    # Add the latest message from the user
+    prompt = template.format(instruction=message, response="")
+    print(prompt)
+
+    # Combine history with the latest prompt
+    final_prompt = formatted_history + prompt
+    print(final_prompt)
+
+    # Generate response from the model
+    response = gemma_lm.generate(final_prompt, max_length=256)
+    # Only keep the generated response
+    response = response.split("Response:")[1].strip()
+
+    print(response)
+
+    # Extract and return the generated response text
+    return response  # Adjust this if your model's output structure differs
+
+# Create the Gradio chat interface
+interface = gr.ChatInterface(
+    fn=generate_response,  # Function that generates responses
+    chatbot=gr.Chatbot(height=300),  # Chatbot UI component
+    textbox=gr.Textbox(placeholder="Hello, am Sage, your mental health advisor", container=False, scale=7),
+    title="Local Model Chat Bot",
+    retry_btn=None,  # Disable retry button
+    undo_btn="Delete Previous",  # Enable undo button
+    clear_btn="Clear"  # Enable clear button
+)
+
+# Launch the Gradio app
+interface.launch(share=True)

requirements.txt

@@ -1,65 +0,0 @@
-aiofiles==23.2.1
-annotated-types==0.7.0
-anyio==4.4.0
-certifi==2024.7.4
-charset-normalizer==3.3.2
-click==8.1.7
-contourpy==1.3.0
-cycler==0.12.1
-distro==1.9.0
-fastapi==0.112.2
-ffmpy==0.4.0
-filelock==3.15.4
-fonttools==4.53.1
-fsspec==2024.6.1
-gradio==4.42.0
-gradio_client==1.3.0
-h11==0.14.0
-httpcore==1.0.5
-httpx==0.27.2
-huggingface-hub==0.24.6
-idna==3.8
-importlib_resources==6.4.4
-Jinja2==3.1.4
-jiter==0.5.0
-kiwisolver==1.4.5
-markdown-it-py==3.0.0
-MarkupSafe==2.1.5
-matplotlib==3.9.2
-mdurl==0.1.2
-numpy==2.1.0
-openai==1.42.0
-orjson==3.10.7
-packaging==24.1
-pandas==2.2.2
-pillow==10.4.0
-pydantic==2.8.2
-pydantic_core==2.20.1
-pydub==0.25.1
-Pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-multipart==0.0.9
-pytz==2024.1
-PyYAML==6.0.2
-regex==2024.7.24
-requests==2.32.3
-rich==13.8.0
-ruff==0.6.2
-safetensors==0.4.4
-semantic-version==2.10.0
-shellingham==1.5.4
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.2
-tokenizers==0.19.1
-tomlkit==0.12.0
-tqdm==4.66.5
-transformers==4.44.2
-typer==0.12.5
-typing_extensions==4.12.2
-tzdata==2024.1
-urllib3==2.2.2
-uvicorn==0.30.6
-websockets==12.0