joelelangovan commited on
Commit
8ff118b
·
verified ·
1 Parent(s): 6a0628d

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +54 -58
app.py CHANGED
@@ -1,64 +1,60 @@
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
+ from transformers import AutoModelForCausalLM, AutoTokenizer
3
+ import torch
4
+
5
+ # Load model and tokenizer
6
+ model_name = "joelelangovan/tamil-llama-genesis-finetuned"
7
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
8
+ model = AutoModelForCausalLM.from_pretrained(
9
+ model_name,
10
+ device_map="auto",
11
+ torch_dtype=torch.float16,
12
+ )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
 
14
+ def generate_response(instruction, temperature=0.7, max_length=512):
15
+ # Format the input text
16
+ input_text = f"### Instruction: {instruction}\n\n### Response:"
17
+
18
+ # Tokenize
19
+ inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
20
+
21
+ # Generate
22
+ outputs = model.generate(
23
+ **inputs,
24
+ max_length=max_length,
25
+ num_return_sequences=1,
26
  temperature=temperature,
27
+ do_sample=True,
28
+ pad_token_id=tokenizer.eos_token_id
29
+ )
30
+
31
+ # Decode and return response
32
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
33
+ # Remove the instruction part from response
34
+ response = response.split("### Response:")[-1].strip()
35
+ return response
36
+
37
+ # Example prompts
38
+ example_prompts = [
39
+ ["ஆதியாகமம் 1:1 வசனத்தின் பொருளை விளக்குங்கள்"],
40
+ ["ஆதியாகமம் 1:2 வசனத்தை தமிழில் விவரிக்கவும்"],
41
+ ["ஆதியாகமம் 1:3 வசனத்தின் முக்கிய கருத்து என்ன?"]
42
+ ]
43
+
44
+ # Create Gradio interface
45
+ demo = gr.Interface(
46
+ fn=generate_response,
47
+ inputs=[
48
+ gr.Textbox(label="கேள்வி / வினா", placeholder="உங்கள் கேள்வியை இங்கே உள்ளிடவும்..."),
49
+ gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
50
+ gr.Slider(minimum=64, maximum=1024, value=512, step=64, label="Max Length"),
51
  ],
52
+ outputs=gr.Textbox(label="பதில்"),
53
+ title="Tamil LLaMA - ஆதியாகமம் விளக்க உதவி",
54
+ description="ஆதியாகமம் முதல் அதிகாரம் பற்றிய கேள்விகளுக்கு விளக்கம் அளிக்கும் AI மாதிரி",
55
+ examples=example_prompts,
56
+ allow_flagging="never",
57
  )
58
 
59
+ # Launch the demo
60
+ demo.launch()