Spaces:
Sleeping
Sleeping
File size: 1,589 Bytes
f2a274f e22fbd5 f2a274f e22fbd5 f672f45 e22fbd5 665ae8a d9f7b70 f2a274f |
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 |
import gradio as gr
import pandas as pd
#Models:
# IlyaGusev/saiga_llama3_8b
# Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
# TinyLlama
# Google-gemma-2-27b-it
# mistralai/Mistral-Nemo-Instruct-2407
# Vikhrmodels/Vikhr-Qwen-2.5-0.5b-Instruct
benchmark_data = {
'Model': [
'TheBloke/llama3-13b', # LLaMA3
'Vikhrmodels/Vikhr-Nemo-12B', # Vikhr
'TinyLLaMA/TinyLlama-1.1B', # TinyLLaMA
'mistralai/Mistral-7B-instruct', # Mistral
'Qwen/Qwen-7B' # Qwen
],
'Creativity Score': [
37.75, # LLaMA3
46.00, # Vikhr
6.50, # TinyLLaMA
23.75, # Mistral
8.25 # Qwen
],
'Diversity Score': [
49.50, # LLaMA3
52.00, # Vikhr
14.50, # TinyLLaMA
38.50, # Mistral
15.55 # Qwen
],
'Relevance Score': [
79.25, # LLaMA3
87.50, # Vikhr
18.50, # TinyLLaMA
76.75, # Mistral
34.25 # Qwen
],
'Average Score': [
55.50, # LLaMA3
61.83, # Vikhr
13.17, # TinyLLaMA
46.33, # Mistral
19.35 # Qwen
]
}
def display_results():
df = pd.DataFrame(benchmark_data)
return df
# Create the interface
with gr.Blocks() as demo:
gr.Markdown("# Model Benchmark Results")
# Display results in a DataFrame
output = gr.Dataframe(
headers=["Model", "Creativity Score", "Coherence Score", "Diversity Score"],
interactive=True
)
if __name__ == "__main__":
demo.launch() |