Spaces:
Runtime error
Runtime error
File size: 3,366 Bytes
ffd7fc8 0296b4c ffd7fc8 87eacbb 9bd4066 87eacbb 04e5312 da8f148 c9e18f8 04e5312 c9e18f8 b922632 ffd7fc8 3329c24 14b2ec7 87eacbb ffd7fc8 |
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 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
from huggingface_hub import InferenceClient
import gradio as gr
from deep_translator import GoogleTranslator
# Initialize the InferenceClient and the translators
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
translator_to_en = GoogleTranslator(source='hindi', target='english')
translator_to_ar = GoogleTranslator(source='english', target='hindi')
def format_prompt(message, history):
prompt = "<s>"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(prompt, history, temperature=0.1, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
# Translate the Arabic prompt to English
translated_prompt = translator_to_en.translate(prompt)
formatted_prompt = format_prompt(translated_prompt, history)
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield translator_to_ar.translate(output) # Translate the response back to Arabic
return output
additional_inputs=[
gr.Slider(
label="Temperature",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="Higher values produce more diverse outputs",
),
gr.Slider(
label="Max new tokens",
value=256,
minimum=0,
maximum=1048,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p (nucleus sampling)",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
)
]
examples = [
["How many languages can you accept input"],
["Tell me about sarcopenia and how to avoid it"],
["Give me a low carb food menu for a day"],
["Give me an exercise plan for a week that include resistance training and cardio"],
]
# Custom title component with an additional line and color change
title = """
<div style='text-align: center;'>
<div style='font-weight: bold; color: red; font-size: 24px;'>A Multilingual Chatbot accept input in any language, answers in Hindi</div>
<div style='font-size: 18px;'>Large language model mistralai/Mistral-7B-Instruct-v0.3</div>
</div>
"""
gr.ChatInterface(
fn=generate,
chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
additional_inputs=additional_inputs,
#gr.Markdown("**Hindi_Mistral8-7b**"), # Title in bold
title=title,
examples=examples
).launch(show_api=True) |