Duplicate from daniloedu/chat_llm_v2

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,14 @@
+---
+title: Chat Llm V2
+emoji: 🦀
+colorFrom: purple
+colorTo: red
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: daniloedu/chat_llm_v2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,49 @@
+import os
+import requests
+import gradio as gr
+from dotenv import load_dotenv
+from transformers import AutoTokenizer
+
+load_dotenv()
+
+model_name = "tiiuae/falcon-7b-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+API_URL = "https://api-inference.huggingface.co/models/tiiuae/falcon-7b-instruct"
+headers = {"Authorization": f"Bearer {os.getenv('HF_API_KEY')}"}
+
+def format_chat_prompt(message, instruction):
+    prompt = f"System:{instruction}\nUser: {message}\nAssistant:"
+    return prompt
+
+def query(payload):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
+    
+def respond(message, instruction="A conversation between a user and an AI assistant. The assistant gives helpful and honest answers."):
+    MAX_TOKENS = 1024  # limit for the model
+    prompt = format_chat_prompt(message, instruction)
+    # Check if the prompt is too long and, if so, truncate it
+    num_tokens = len(tokenizer.encode(prompt))
+    if num_tokens > MAX_TOKENS:
+        # Truncate the prompt to fit within the token limit
+        prompt = tokenizer.decode(tokenizer.encode(prompt)[-MAX_TOKENS:])
+    
+    response = query({"inputs": prompt})
+    generated_text = response[0]['generated_text']
+    assistant_message = generated_text.split("Assistant:")[-1]
+    assistant_message = assistant_message.split("User:")[0].strip()  # Only keep the text before the first "User:"
+    return assistant_message
+
+iface = gr.Interface(
+    respond,
+    inputs=[
+        gr.inputs.Textbox(label="Your question"), 
+        gr.inputs.Textbox(label="System message", lines=2, default="A conversation between a user and an AI assistant. The assistant gives helpful and honest answers.")
+    ],
+    outputs=[
+        gr.outputs.Textbox(label="AI's response")
+    ],
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,7 @@
+python-dotenv
+gradio
+transformers
+torch
+einops
+accelerate
+requests