File size: 1,566 Bytes
fe41391
 
5c1306e
 
6091007
 
 
 
5c1306e
 
 
fe41391
 
aba9e8d
5c1306e
fe41391
 
5c1306e
 
 
 
 
 
fe41391
5c1306e
 
 
 
 
fe41391
 
 
 
 
 
 
 
0a06673
fe41391
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
import gradio as gr
from transformers import pipeline
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
# model_name = "AdaptLLM/law-LLM"
model_name = "google/gemma-2b"
# model_name = "mistralai/Mistral-7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)


# Load the llama2 LLM model
# model = pipeline("text-generation", model="llamalanguage/llama2", tokenizer="llamalanguage/llama2")
# model = pipeline("text-generation", model="mistralai/Mistral-7B-v0.1", tokenizer="meta-llama/Llama-2-7b-chat-hf")

# Define the chat function that uses the LLM model
# def chat_interface(input_text):
#     response = model(input_text, max_length=100, return_full_text=True)[0]["generated_text"]
#     response_words = response.split()
#     return response_words

# Define the chat function that uses the Mistral-7B-v0.1 model
def chat_interface(input_text):
    inputs = tokenizer.encode(input_text, return_tensors="pt")
    outputs = model.generate(inputs, max_length=100)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response


# Create the Gradio interface
iface = gr.Interface(
    fn=chat_interface,
    inputs=gr.inputs.Textbox(lines=2, label="Input Text"),
    outputs=gr.outputs.Textbox(label="Output Text"),
    title="Chat Interface",
    description="Enter text and get a response using the LLM model",
    # live=True  # Enable live updates
)

# Launch the interface using Hugging Face Spaces
iface.launch(share=True)