Upload 3 files

README.md

@@ -1,13 +1,10 @@
 ---
-title: Chat With TrendyolLLM
-emoji: 😻
+title: TrendyolLLM-Chat
+emoji: 🛒
 colorFrom: red
-colorTo: purple
+colorTo: yellow
 sdk: gradio
-sdk_version: 4.18.0
+sdk_version: 4.7.1
 app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+pinned: true
+---

app.py

@@ -0,0 +1,62 @@
+import gradio as gr
+import os
+from pathlib import Path
+import argparse
+from huggingface_hub import snapshot_download
+from llama_cpp import Llama
+
+repo_name = 'tolgadev/Trendyol-LLM-7b-chat-v0.1-GGUF'
+model_file = "trendyol-llm-7b-chat-v0.1.Q5_K_M.gguf"
+
+snapshot_download(repo_id=repo_name, local_dir=".", allow_patterns=model_file)
+
+DEFAULT_MODEL_PATH = model_file
+llm = Llama(model_path=model_file, model_type="llama")
+
+def predict(input, chatbot, max_length, top_p, temperature, history):
+    chatbot.append((input, ""))
+    response = ""
+    history.append(input)
+
+    for output in llm(input, stream=True, temperature=temperature, top_p=top_p, max_tokens=max_length, ):
+        piece = output['choices'][0]['text']
+        response += piece
+        chatbot[-1] = (chatbot[-1][0], response)
+
+        yield chatbot, history
+
+    history.append(response)
+    yield chatbot, history
+
+
+def reset_user_input():
+    return gr.update(value="")
+
+def reset_state():
+    return [], []
+
+with gr.Blocks() as demo:
+    gr.HTML("""<h1 align="center">TrendyolLLM Chatbot Demo</h1>
+            <h3 align="center">This is unofficial demo of [```tolgadev/Trendyol-LLM-7b-chat-v0.1-GGUF```](https://huggingface.co/tolgadev/Trendyol-LLM-7b-chat-v0.1-GGUF) model based on ```LLama2 architecture```.</h3>""")
+
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        with gr.Column(scale=4):
+            user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=8, elem_id="user_input")
+            submitBtn = gr.Button("Submit", variant="primary", elem_id="submit_btn")
+        with gr.Column(scale=1):
+            max_length = gr.Slider(0, 256, value=64, step=1.0, label="Maximum Length", interactive=True)
+            top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
+            temperature = gr.Slider(0, 2.0, value=0.95, step=0.01, label="Temperature", interactive=True)
+            emptyBtn = gr.Button("Clear History")
+
+    history = gr.State([])
+
+    submitBtn.click(
+        predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True
+    )
+    submitBtn.click(reset_user_input, [], [user_input])
+
+    emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
+
+demo.queue().launch(share=False, inbrowser=True)

requirements.txt

@@ -0,0 +1,3 @@
+llama-cpp-python==0.2.11
+huggingface-hub==0.14.1
+gradio==3.32.0