|
|
from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM |
|
|
from peft import PeftModel, PeftConfig |
|
|
import torch |
|
|
import gradio as gr |
|
|
import random |
|
|
from textwrap import wrap |
|
|
|
|
|
EXAMPLES = [ |
|
|
["Hey Falcon! Any recommendations for my holidays in Abu Dhabi?"], |
|
|
["What's the Everett interpretation of quantum mechanics?"], |
|
|
["Give me a list of the top 10 dive sites you would recommend around the world."], |
|
|
["Can you tell me more about deep-water soloing?"], |
|
|
["Can you write a short tweet about the release of our latest AI model, Falcon LLM?"] |
|
|
] |
|
|
|
|
|
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
base_model_id = "tiiuae/falcon-7b-instruct" |
|
|
model_directory = "Tonic/GaiaMiniMed" |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True, padding_side="left") |
|
|
model_config = AutoConfig.from_pretrained(base_model_id) |
|
|
peft_model = AutoModelForCausalLM.from_pretrained(model_directory, config=model_config) |
|
|
peft_model = PeftModel.from_pretrained(peft_model, model_directory) |
|
|
|
|
|
def format_prompt(message, history, system_prompt): |
|
|
prompt = "" |
|
|
if system_prompt: |
|
|
prompt += f"System: {system_prompt}\n" |
|
|
for user_prompt, bot_response in history: |
|
|
prompt += f"User: {user_prompt}\n" |
|
|
prompt += f"Falcon: {bot_response}\n" |
|
|
prompt += f"""User: {message} |
|
|
Falcon:""" |
|
|
return prompt |
|
|
|
|
|
seed = 42 |
|
|
|
|
|
def generate( |
|
|
prompt, history, system_prompt="", temperature=0.9, max_new_tokens=500, top_p=0.95, repetition_penalty=1.0, |
|
|
): |
|
|
temperature = float(temperature) |
|
|
if temperature < 1e-2: |
|
|
temperature = 1e-2 |
|
|
top_p = float(top_p) |
|
|
global seed |
|
|
generate_kwargs = dict( |
|
|
temperature=temperature, |
|
|
max_new_tokens=max_new_tokens, |
|
|
top_p=top_p, |
|
|
repetition_penalty=1.0, |
|
|
stop_sequences="[END]", |
|
|
do_sample=True, |
|
|
seed=seed, |
|
|
) |
|
|
seed = seed + 1 |
|
|
formatted_prompt = format_prompt(prompt, history, system_prompt) |
|
|
|
|
|
try: |
|
|
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 |
|
|
|
|
|
for stop_str in STOP_SEQUENCES: |
|
|
if output.endswith(stop_str): |
|
|
output = output[:-len(stop_str)] |
|
|
output = output.rstrip() |
|
|
yield output |
|
|
yield output |
|
|
except Exception as e: |
|
|
raise gr.Error(f"Error while generating: {e}") |
|
|
return output |
|
|
|
|
|
|
|
|
additional_inputs=[ |
|
|
gr.Textbox("", label="Optional system prompt"), |
|
|
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=3000, |
|
|
step=64, |
|
|
interactive=True, |
|
|
info="The maximum numbers of new tokens", |
|
|
), |
|
|
gr.Slider( |
|
|
label="Top-p (nucleus sampling)", |
|
|
value=0.90, |
|
|
minimum=0.01, |
|
|
maximum=0.99, |
|
|
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", |
|
|
) |
|
|
] |
|
|
|
|
|
|
|
|
with gr.Blocks() as demo: |
|
|
with gr.Row(): |
|
|
with gr.Column(scale=0.4): |
|
|
gr.Image("better_banner.jpeg", elem_id="banner-image", show_label=False) |
|
|
with gr.Column(): |
|
|
gr.Markdown( |
|
|
|
|
|
"You can use this Space to test out the current model [(Tonic/GaiaMiniMed)](https://huggingface.co/Tonic/GaiaMiniMed) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)." |
|
|
) |
|
|
|
|
|
gr.ChatInterface( |
|
|
generate, |
|
|
examples=EXAMPLES, |
|
|
additional_inputs=additional_inputs, |
|
|
) |
|
|
|
|
|
demo.queue(concurrency_count=100, api_open=False).launch(show_api=False) |
|
|
|
