This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# coding: utf-8 | |
# In[3]: | |
#!pip install --upgrade numpy | |
get_ipython().system('pip install numpy==1.24') | |
# In[4]: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def create_batches(records, block_size, num_batches, eos_token_id): | |
random.shuffle(records) | |
# Adding eos_token_id to each record and then checking if it fits in the block | |
available_records = [[i, record + [eos_token_id]] for i, record in enumerate(records) if len(record) + 1 <= block_size] | |
def fill_sequence(sequence, available_records, space_avail): | |
if not available_records or space_avail <= 0: | |
return sequence, available_records, space_avail |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#https://gist.githubusercontent.com/thistleknot/raw/mamba_trainer.py | |
#SimplerMambaSSM | |
#https://colab.research.google.com/drive/1g9qpeVcFa0ca0cnhmqusO4RZtQdh9umY#scrollTo=2lECw6S4N7cn | |
#!pip install mamba-ssm causal-conv1d | |
#resources | |
#!wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt | |
#https://github.com/havenhq/mamba-chat/blob/main/trainer/mamba_trainer.py | |
#https://github.com/state-spaces/mamba/blob/main/mamba_ssm/models/mixer_seq_simple.py |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#https://gist.githubusercontent.com/thistleknot/raw/mamba_trainer.py | |
#!pip install mamba-ssm causal-conv1d | |
#resources | |
#!wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt | |
#https://github.com/havenhq/mamba-chat/blob/main/trainer/mamba_trainer.py | |
#https://github.com/state-spaces/mamba/blob/main/mamba_ssm/models/mixer_seq_simple.py | |
#https://github.com/state-spaces/mamba/blob/main/mamba_ssm/modules/mamba_simple.py | |
#https://huggingface.co/clibrain/mamba-2.8b-instruct-openhermes |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from textblob import TextBlob | |
from sklearn.feature_extraction.text import TfidfVectorizer | |
import numpy as np | |
import scipy.stats as stats | |
original_text = [ | |
"Don't incur technical debt, fully define what is proposed.", | |
"Prefer O'Reilly style writing using examples of time-tested failproof boilerplate solutions with docstring comments.", | |
"Assume user's expertise: Masters in Data Science, Classical Philosophy, and proficiency in AI, Python, SQL.", | |
"Always deliver production ready code.", |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
"""SimplerMambaSSM.ipynb | |
Automatically generated by Colaboratory. | |
#pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu121 | |
Original file is located at | |
https://colab.research.google.com/drive/1g9qpeVcFa0ca0cnhmqusO4RZtQdh9umY | |
""" | |
#!pip install mamba-ssm causal-conv1d | |
#!wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt | |
#!mkdir differentattention |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
"""SimplerMambaSSM.ipynb | |
Automatically generated by Colaboratory. | |
Original file is located at | |
https://colab.research.google.com/drive/1g9qpeVcFa0ca0cnhmqusO4RZtQdh9umY | |
""" | |
#!pip install mamba-ssm causal-conv1d |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#export LD_LIBRARY_PATH=/usr/local/cuda/targets/x86_64-linux/lib/ | |
from transformers import AutoTokenizer, AutoModelForCausalLM | |
from transformers import BitsAndBytesConfig | |
from datasets import load_dataset | |
import json | |
import torch | |
from tqdm import tqdm | |
if torch.cuda.is_available(): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# coding: utf-8 | |
import torch | |
import torch.nn.functional as F | |
from transformers import GPTNeoForCausalLM, AutoTokenizer | |
from datasets import load_dataset | |
from sklearn.model_selection import train_test_split | |
import pandas as pd | |
import numpy as np |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# coding: utf-8 | |
import torch | |
import torch.nn.functional as F | |
from transformers import GPTNeoForCausalLM, AutoTokenizer | |
from datasets import load_dataset | |
from sklearn.model_selection import train_test_split | |
import pandas as pd | |
import numpy as np |