Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+frpc_linux_amd64 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,63 +1,60 @@
 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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    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]})
-
-    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
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        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)",
-        ),
-    ],
-)
+import os
+import keras_nlp
+
+
+# Set Kaggle API credentials (if needed)
+# Set Kaggle API credentials
+
+os.environ["KAGGLE_USERNAME"] = "rogerkorantenng"
+os.environ["KAGGLE_KEY"] = "9a33b6e88bcb6058b1281d777fa6808d"
+
+
+# Set the JAX backend and configure memory
+os.environ["KERAS_BACKEND"] = "tensorflow"
+os.environ["XLA_PYTHON_CLIENT_MEM_FRACTION"] = "1.00"
+
+# Load the GemmaCausalLM model
+gemma_lm = keras_nlp.models.GemmaCausalLM.from_preset("gemma_2b_en")
+
+# Load LoRA weights if you have them
+LoRA_weights_path = "model.lora.h5"
+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
 
+# 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="")
+
+    # Combine history with the latest prompt
+    final_prompt = formatted_history + prompt
+
+    # Generate response from the model
+    response = gemma_lm.generate(final_prompt, max_length=256)
+
+    # Extract and return the generated response text
+    return response[0]  # 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="You can ask me anything", 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
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio app
+interface.launch(share=True)

frpc_linux_amd64

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb74b665633589410540c49dfcef5b6f0fd4a9bd7c9558bcdee2f0e43da0774d
+size 11374592

model.lora.h5

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