rezaenayati commited on
Commit
2eb4c0d
·
verified ·
1 Parent(s): a8cbb7b

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +47 -49
app.py CHANGED
@@ -1,64 +1,62 @@
1
- import gradio as gr
2
- from huggingface_hub import InferenceClient
 
 
 
 
 
 
 
 
 
3
 
4
- """
5
- 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
6
- """
7
- client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
8
 
 
 
9
 
10
- def respond(
11
- message,
12
- history: list[tuple[str, str]],
13
- system_message,
14
- max_tokens,
15
- temperature,
16
- top_p,
17
- ):
18
- messages = [{"role": "system", "content": system_message}]
19
 
20
- for val in history:
21
- if val[0]:
22
- messages.append({"role": "user", "content": val[0]})
23
- if val[1]:
24
- messages.append({"role": "assistant", "content": val[1]})
25
 
26
- messages.append({"role": "user", "content": message})
27
 
28
- response = ""
29
 
30
- for message in client.chat_completion(
31
- messages,
32
- max_tokens=max_tokens,
33
- stream=True,
34
- temperature=temperature,
35
- top_p=top_p,
36
- ):
37
- token = message.choices[0].delta.content
38
 
39
- response += token
40
- yield response
 
41
 
 
42
 
43
- """
44
- For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
45
- """
46
  demo = gr.ChatInterface(
47
- respond,
48
- additional_inputs=[
49
- gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
50
- gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
51
- gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
52
- gr.Slider(
53
- minimum=0.1,
54
- maximum=1.0,
55
- value=0.95,
56
- step=0.05,
57
- label="Top-p (nucleus sampling)",
58
- ),
59
  ],
 
 
 
60
  )
61
 
62
-
63
  if __name__ == "__main__":
64
- demo.launch()
 
1
+ import gradio as gr
2
+ import torch
3
+ from transformers import AutoTokenizer, AutoModelForCausalLM
4
+ from peft import PeftModel
5
+
6
+ base_model = AutoModelForCausalLM.from_pretrained(
7
+ "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
8
+ torch_dtype=torch.float16,
9
+ device_map="auto",
10
+ load_in_4bit=True
11
+ )
12
 
13
+ #tokenizer
14
+ tokenizer = AutoTokenizer.from_pretrained("unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit")
 
 
15
 
16
+ #LoRA adaptors
17
+ model = PeftModel.from_pretrained(base_model, "rezaenayati/RezAi-Model")
18
 
19
+ def chat_with_rezAi(messages, history):
20
+ conversation = "<|start_header_id|>system<|end_header_id|>\nYou are Reza Enayati, a Computer Science student and entrepreneur from Los Angeles, who is eager to work as a software engineer or machine learning engineer. Answer these questions as if you are in an interview.<|eot_id|>"
 
 
 
 
 
 
 
21
 
22
+ for user_msg, assistant_msg in history:
23
+ conversation += f"<|start_header_id|>user<|end_header_id|>\n{user_msg}<|eot_id|>"
24
+ conversation += f"<|start_header_id|>assistant<|end_header_id|>\n{assistant_msg}<|eot_id|>"
 
 
25
 
26
+ conversation += f"<|start_header_id|>user<|end_header_id|>\n{message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n"
27
 
28
+ inputs = tokenizer([conversation], return_tensors="pt")
29
 
30
+ with torch.no_grad():
31
+ outputs = model.generate(
32
+ **inputs,
33
+ max_new_tokens=128,
34
+ temperature=0.5,
35
+ do_sample=True,
36
+ pad_token_id=tokenizer.eos_token_id
37
+ )
38
 
39
+ #get response
40
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
41
+ new_response = response.split("<|start_header_id|>assistant<|end_header_id|>")[-1].strip()
42
 
43
+ return new_response
44
 
 
 
 
45
  demo = gr.ChatInterface(
46
+ fn=chat_with_rezAi,
47
+ title="💬 Chat with RezAI",
48
+ description="Hi! I'm RezAI. Ask me about his technical background, projects, or experience!",
49
+ examples=[
50
+ "Tell me about your background",
51
+ "What programming languages do you know?",
52
+ "Walk me through your Pizza Guys project",
53
+ "What's your experience with machine learning?",
54
+ "How did you get into computer science?"
 
 
 
55
  ],
56
+ retry_btn=None,
57
+ undo_btn="Delete Previous",
58
+ clear_btn="Clear Chat",
59
  )
60
 
 
61
  if __name__ == "__main__":
62
+ demo.launch()