4 6 14

Cody Steinmetz PRO

codys12

AI & ML interests

None yet

Recent Activity

updated a Space about 8 hours ago

codys12/NetCom-to-WooComerce

published an article 1 day ago

All LLMs Will Be Sparse BitNet Hybrids

updated a model 2 days ago

codys12/bitnet-r1-llama-8b

View all activity

Organizations

codys12's activity

updated a Space about 8 hours ago

NetCom To WooComerce

🏃

CSV conversion tool

published an article 1 day ago

Article

All LLMs Will Be Sparse BitNet Hybrids

•

1 day ago

• 3

updated a model 2 days ago

codys12/bitnet-r1-llama-8b

Text Generation • Updated 2 days ago • 111 • 3

posted an update 2 days ago

Post

1451

Introducing bitnet-r1-llama-8b and bitnet-r1-qwen-32b preview! These models are the first successful sub 1-billion-token finetune to BitNet architecture. We discovered that by adding an aditional input RMSNorm to each linear, you can finetune directly to BitNet with fast convergence to original model performance!

We are working on a pull request to use this extra RMS for any model.

To test these models now, install this fork of transformers:

pip install git+https://github.com/Codys12/transformers.git

Then load the models and test:

from transformers import (AutoModelForCausalLM, AutoTokenizer)

model_id = "codys12/bitnet-r1-qwen-32b" 
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="cuda",
)
tokenizer = AutoTokenizer.from_pretrained(model_id, padding_side="left")

bitnet-r1-llama-8b and bitnet-r1-llama-32b were trained on ~ 300M and 200M tokens of the open-thoughts/OpenThoughts-114k dataset respectively, and were still significantly improving at the end of training. This preview simply demonstrates that the concept works, for future training runs we will leave the lm_head unquantized and align the last hidden state with the original model.

Huge thanks to the team that made this possible:
Gavin Childress, Aaron Herbst, Gavin Jones, Jasdeep Singh, Eli Vang, and Keagan Weinstock from the MSOE AI Club.