selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2025-12-20 20:29:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

organize trails

Browse Source
This commit is contained in:
Gokul Mohanarangan
2023-07-25 10:15:16 +05:30
parent 25f34bf9e5
commit 1672be0383
8 changed files with 105 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
trials/__init__.py Normal file
View File

13
trials/api.py
View File

@@ -1,11 +1,13 @@
import requests
import spacy
# Enter the Machine where the LLM is hosted
LLM_MACHINE_IP = ""
# This is the URL of text-generation-webui
URL = "http://216.153.52.83:5000/api/v1/generate"
URL = f"http://{LLM_MACHINE_IP}:5000/api/v1/generate"
headers = {
"Content-Type": "application/json"
"Content-Type": "application/json"
}
@@ -23,7 +25,7 @@ def split_text_file(filename, token_count):
while start_index < total_tokens:
end_index = start_index + token_count
part_tokens = doc[start_index:end_index-5]
part_tokens = doc[start_index:end_index - 5]
part = ' '.join(token.text for token in part_tokens)
parts.append(part)
start_index = end_index
@@ -33,7 +35,6 @@ def split_text_file(filename, token_count):
final_summary = ""
parts = split_text_file("transcript.txt", 1600)
previous_summary = ""
for part in parts:
prompt = f"""
@@ -52,5 +53,5 @@ for part in parts:
except Exception as e:
print(str(e))
with open("sum.txt", "w") as sum:
sum.write(" ".join(final_summary))
with open("summary.txt", "w") as sum:
sum.write(" ".join(final_summary))

125
trials/gpt2.py
View File

@@ -1,65 +1,66 @@
# # Approach 1
# from transformers import GPTNeoForCausalLM, GPT2Tokenizer
#
# model_name = 'EleutherAI/gpt-neo-1.3B'
# tokenizer = GPT2Tokenizer.from_pretrained(model_name)
# model = GPTNeoForCausalLM.from_pretrained(model_name)
#
# conversation = """
# Summarize the following conversation in 3 key sentences:
#
# We 're joined next by Thomas Curian , CEO of Google Cloud , and Alexander Wang , CEO and founder of Scale AI .
# Thomas joined Google in November 2018 as the CEO of Google Cloud . Prior to Google , Thomas spent 22 years at Oracle , where most recently he was president of product development .
# Before that , Thomas worked at McKinsey as a business analyst and engagement manager . His nearly 30 years of experience have given him a deep knowledge of engineering enterprise relationships and leadership of large organizations .
# Thomas 's degrees include an MBA in administration and management from Stanford University , as an RJ Miller scholar and a BSEE in electrical engineering and computer science from Princeton University , where he graduated suma cum laude .
# Thomas serves as a member of the Stanford graduate School of Business Advisory Council and Princeton University School of Engineering Advisory Council .
# Please welcome to the stage , Thomas Curian and Alexander Wang . This is a super exciting conversation . Thanks for being here , Thomas .
# """
#
# input_ids = tokenizer.encode(conversation, return_tensors='pt')
#
# output = model.generate(input_ids,
# max_length=30,
# num_return_sequences=1)
#
# caption = tokenizer.decode(output[0], skip_special_tokens=True)
# print("Caption:", caption[len(input_ids):])
# Approach 1
from transformers import GPTNeoForCausalLM, GPT2Tokenizer
#
# # Approach 2
# import torch
# from transformers import GPT2LMHeadModel, GPT2Tokenizer
#
# model_name = "gpt2"
# tokenizer = GPT2Tokenizer.from_pretrained(model_name)
# model = GPT2LMHeadModel.from_pretrained(model_name)
#
# model.eval()
#
# text = """
# You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple . If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody . Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me . So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody . And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . "
# """
#
# tokenizer.pad_token = tokenizer.eos_token
# input_ids = tokenizer.encode(text,
# max_length=100,
# truncation=True,
# return_tensors="pt")
# attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
# output = model.generate(input_ids,
# max_new_tokens=20,
# num_return_sequences=1,
# num_beams=2,
# attention_mask=attention_mask)
#
# chapter_titles = [tokenizer.decode(output[i], skip_special_tokens=True) for i in range(output.shape[0])]
# for i, title in enumerate(chapter_titles):
# print("Caption: ", title)
model_name = 'EleutherAI/gpt-neo-1.3B'
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPTNeoForCausalLM.from_pretrained(model_name)
conversation = """
Summarize the following conversation in 3 key sentences:
We 're joined next by Thomas Curian , CEO of Google Cloud , and Alexander Wang , CEO and founder of Scale AI .
Thomas joined Google in November 2018 as the CEO of Google Cloud . Prior to Google , Thomas spent 22 years at Oracle , where most recently he was president of product development .
Before that , Thomas worked at McKinsey as a business analyst and engagement manager . His nearly 30 years of experience have given him a deep knowledge of engineering enterprise relationships and leadership of large organizations .
Thomas 's degrees include an MBA in administration and management from Stanford University , as an RJ Miller scholar and a BSEE in electrical engineering and computer science from Princeton University , where he graduated suma cum laude .
Thomas serves as a member of the Stanford graduate School of Business Advisory Council and Princeton University School of Engineering Advisory Council .
Please welcome to the stage , Thomas Curian and Alexander Wang . This is a super exciting conversation . Thanks for being here , Thomas .
"""
input_ids = tokenizer.encode(conversation, return_tensors='pt')
output = model.generate(input_ids,
max_length=30,
num_return_sequences=1)
caption = tokenizer.decode(output[0], skip_special_tokens=True)
print("Caption:", caption[len(input_ids):])
# Approach 2
import torch
from transformers import GPT2LMHeadModel, GPT2Tokenizer
model_name = "gpt2"
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)
model.eval()
text = """
You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple . If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody . Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me . So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody . And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . "
"""
tokenizer.pad_token = tokenizer.eos_token
input_ids = tokenizer.encode(text,
max_length=100,
truncation=True,
return_tensors="pt")
attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
output = model.generate(input_ids,
max_new_tokens=20,
num_return_sequences=1,
num_beams=2,
attention_mask=attention_mask)
chapter_titles = [tokenizer.decode(output[i], skip_special_tokens=True) for i in range(output.shape[0])]
for i, title in enumerate(chapter_titles):
print("Caption: ", title)
# Approach 3
import torch
from transformers import GPT2Tokenizer, GPT2LMHeadModel
from transformers import GPT2LMHeadModel, GPT2Tokenizer
def generate_response(conversation, max_length=100):
input_text = ""
@@ -79,20 +80,22 @@ def generate_response(conversation, max_length=100):
response = tokenizer.decode(output[0], skip_special_tokens=True)
return response
if __name__ == "__main__":
# Call appropriate approach from the main while experimenting
model_name = "gpt2"
model = GPT2LMHeadModel.from_pretrained(model_name)
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
sample_chunks = [
"You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple . If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody . Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me . So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody . And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . "
"You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple . If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody . Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me . So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody . And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . "
]
conversation = [
{"role": "system", "content": "Summarize this text" },
{"role": "user", "content": " text : " + sample_chunks[0]},
{"role": "system", "content": "Summarize this text"},
{"role": "user", "content": " text : " + sample_chunks[0]},
]
response = generate_response(conversation)
print("Response:", response)

29
trials/incsum.py
View File

@@ -1,9 +1,11 @@
import spacy
import sys
# Observe the incremental summaries by performing summaries in chunks
with open("transcript.txt") as f:
transcription = f.read()
import spacy
def split_text_file(filename, token_count):
nlp = spacy.load('en_core_web_md')
@@ -26,8 +28,9 @@ def split_text_file(filename, token_count):
return parts
# Set the chunk length here to split the transcript and test
MAX_CHUNK_LENGTH=1000
MAX_CHUNK_LENGTH = 1000
chunks = split_text_file("transcript.txt", MAX_CHUNK_LENGTH)
print("Number of chunks", len(chunks))
@@ -41,19 +44,17 @@ with open("chunks" + str(MAX_CHUNK_LENGTH) + ".txt", "a") as f:
# ex. python incsum.py 1 => will run approach 1
# If no input, will run all approaches
import sys
try:
index = sys.argv[1]
except:
index = None
# Approach 1 : facebook/bart-large-cnn
if index == "1" or index is None:
SUMMARY_MODEL="facebook/bart-large-cnn"
MIN_LENGTH=5
MAX_LENGTH=10
BEAM_SIZE=2
SUMMARY_MODEL = "facebook/bart-large-cnn"
MIN_LENGTH = 5
MAX_LENGTH = 10
BEAM_SIZE = 2
print("Performing chunk summary : " + SUMMARY_MODEL)
@@ -81,7 +82,6 @@ if index == "1" or index is None:
for summary in summaries:
f.write(summary + "\n\n")
# Approach 2
if index == "2" or index is None:
print("Performing chunk summary : " + "gpt-neo-1.3B")
@@ -108,14 +108,14 @@ if index == "2" or index is None:
max_length=max_length,
attention_mask=attention_mask,
pad_token_id=model.config.eos_token_id,
num_beams=4,
length_penalty=2.0,
early_stopping=True)
num_beams=4,
length_penalty=2.0,
early_stopping=True)
summary_ids = output[0, input_length:]
summary = tokenizer.decode(summary_ids, skip_special_tokens=True)
summaries.append(summary)
with open("gptneo1.3B-summaries.txt", "a") as f:
f.write(summary + "\n\n")
f.write(summary + "\n\n")
# Approach 3
if index == "3" or index is None:
@@ -155,4 +155,3 @@ if index == "3" or index is None:
with open("mpt-7b-summaries.txt", "a") as f:
for summary in summaries:
f.write(summary + "\n\n")

13
trials/openai_endpoint.py
View File

@@ -11,14 +11,15 @@ openai.api_key = ""
# to incremental summarize, user prompt used : "summarize this conversation in a few sentences by taking key points"
# max_tokens=300
sample_chunks = ["You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple . If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody . Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me . So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody . And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . ",
" We 're joined next by Thomas Curian , CEO of Google Cloud , and Alexander Wang , CEO and founder of Scale AI . Thomas joined Google in November 2018 as the CEO of Google Cloud . Prior to Google , Thomas spent 22 years at Oracle , where most recently he was president of product development . Before that , Thomas worked at McKinsey as a business analyst and engagement manager . His nearly 30 years of experience have given him a deep knowledge of engineering enterprise relationships and leadership of large organizations . Thomas 's degrees include an MBA in administration and management from Stanford University , as an RJ Miller scholar and a BSEE in electrical engineering and computer science from Princeton University , where he graduated suma cum laude . Thomas serves as a member of the Stanford graduate School of Business Advisory Council and Princeton University School of Engineering Advisory Council . Please welcome to the stage , Thomas Curian and Alexander Wang . This is a super exciting conversation . Thanks for being here , Thomas ."]
sample_chunks = [
"You all just came off of your incredible Google Cloud next conference where you released a wide variety of functionality and features and new products across artisan television and also across the entire sort of cloud ecosystem . You want to just first by walking through , first start by walking through all the innovations that you sort of released and what you 're excited about when you come to Google Cloud ? Now our vision is super simple . If you look at what smartphones did for a consumer , you know they took a computer and internet browser , a communication device , and a camera , and made it so that it 's in everybody 's pocket , so it really brought computation to every person . We feel that , you know , our , what we 're trying to do is take all the technological innovation that Google 's doing , but make it super simple so that everyone can consume it . And so that includes our global data center footprint , all the new types of hardware and large-scale systems we work on , the software that we 're making available for people to do high-scale computation , tools for data processing , tools for cybersecurity , processing , tools for cyber security , tools for machine learning , but make it so simple that everyone can use it . And every step that we do to simplify things for people , we think adoption can grow . And so that 's a lot of what we 've done these last three , four years , and we made a number of announcements that next in machine learning and AI in particular , you know , we look at our work as four elements , how we take our large-scale compute systems that were building for AI and how we make that available to everybody . Second , what we 're doing with the software stacks and top of it , things like jacks and other things and how we 're making those available to everybody . Third is advances because different people have different levels of expertise . Some people say I need the hardware to build my own large language model or algorithm . Other people say , look , I really need to use a building block . You guys give me . So , 30s we 've done a lot with AutoML and we announce new capability for image , video , and translation to make it available to everybody . And then lastly , we 're also building completely packaged solutions for some areas and we announce some new stuff . ",
" We 're joined next by Thomas Curian , CEO of Google Cloud , and Alexander Wang , CEO and founder of Scale AI . Thomas joined Google in November 2018 as the CEO of Google Cloud . Prior to Google , Thomas spent 22 years at Oracle , where most recently he was president of product development . Before that , Thomas worked at McKinsey as a business analyst and engagement manager . His nearly 30 years of experience have given him a deep knowledge of engineering enterprise relationships and leadership of large organizations . Thomas 's degrees include an MBA in administration and management from Stanford University , as an RJ Miller scholar and a BSEE in electrical engineering and computer science from Princeton University , where he graduated suma cum laude . Thomas serves as a member of the Stanford graduate School of Business Advisory Council and Princeton University School of Engineering Advisory Council . Please welcome to the stage , Thomas Curian and Alexander Wang . This is a super exciting conversation . Thanks for being here , Thomas ."]
conversation = [
{"role": "system",
"content": sample_chunks[1]},
{"role": "user",
"content": "summarize this conversation in a few sentences by taking key points"}
{"role": "system",
"content": sample_chunks[1]},
{"role": "user",
"content": "summarize this conversation in a few sentences by taking key points"}
]
model = "gpt-3.5-turbo"

0
trials/whisper-jax/__init__.py Normal file
View File

16
whisjax.py → trials/whisper-jax/whisjax.py
View File

@@ -18,11 +18,11 @@ import nltk
import yt_dlp as youtube_dl
from whisper_jax import FlaxWhisperPipline
from utils.file_utils import download_files, upload_files
from utils.log_utils import logger
from utils.run_utils import config
from utils.text_utilities import post_process_transcription, summarize
from utils.viz_utilities import create_talk_diff_scatter_viz, create_wordcloud
from ...utils.file_utils import download_files, upload_files
from ...utils.log_utils import logger
from ...utils.run_utils import config
from ...utils.text_utilities import post_process_transcription, summarize
from ...utils.viz_utilities import create_talk_diff_scatter_viz, create_wordcloud
nltk.download('punkt', quiet=True)
nltk.download('stopwords', quiet=True)
@@ -30,8 +30,8 @@ nltk.download('stopwords', quiet=True)
WHISPER_MODEL_SIZE = config['DEFAULT']["WHISPER_MODEL_SIZE"]
NOW = datetime.now()
if not os.path.exists('./artefacts'):
os.makedirs('./artefacts')
if not os.path.exists('../../artefacts'):
os.makedirs('../../artefacts')
def init_argparse() -> argparse.ArgumentParser:
@@ -91,7 +91,7 @@ def main():
# Download the audio
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download([args.location])
media_file = "./artefacts/audio.mp3"
media_file = "../artefacts/audio.mp3"
logger.info("Saved downloaded YouTube video to: " + media_file)
else:

10
whisjax_realtime.py → trials/whisper-jax/whisjax_realtime.py
View File

@@ -10,11 +10,11 @@ from pynput import keyboard
from termcolor import colored
from whisper_jax import FlaxWhisperPipline
from utils.file_utils import upload_files
from utils.log_utils import logger
from utils.run_utils import config
from utils.text_utilities import post_process_transcription, summarize
from utils.viz_utilities import create_talk_diff_scatter_viz, create_wordcloud
from ...utils.file_utils import upload_files
from ...utils.log_utils import logger
from ...utils.run_utils import config
from ...utils.text_utilities import post_process_transcription, summarize
from ...utils.viz_utilities import create_talk_diff_scatter_viz, create_wordcloud
WHISPER_MODEL_SIZE = config['DEFAULT']["WHISPER_MODEL_SIZE"]