File size: 1,338 Bytes
02592ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
#!/usr/bin/env python
# coding: utf-8

# In[29]:


import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch


# In[30]:


model = AutoModelForCausalLM.from_pretrained(
    "tiiuae/falcon-7b-instruct",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
    low_cpu_mem_usage=True,
)
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct")


# In[31]:


def generate_text(input_text):
    input_ids = tokenizer.encode(input_text, return_tensors="pt")
    attention_mask = torch.ones(input_ids.shape)
    
    output = model.generate(
        input_ids,
        attention_mask=attention_mask,
        max_length=200,
        do_sample=True,
        top_k=10,
        num_return_sequences=1,
        eos_token_id=tokenizer.eos_token_id,
    )
    
    output_text = tokenizer.decode(output[0], skip_special_tokens=True)
    print(output_text)
    
    #Remove Prompt Echo from Generated Text
    cleaned_output_text = output_text.replace(input_text, "")
    return cleaned_output_text


# In[32]:


text_generation_interface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.inputs.Textbox(label="Input Text"),
    ],
    outputs=gr.inputs.Textbox(label="Generated Text"),
    title="Falcon-7B Instruct",
).launch()


# In[25]:


gr.close_all()