“A Stochastic Parrot, flat design, vector art” — Stable Diffusion XL
This repository contains Stability AI’s ongoing development of the StableLM series of language models and will be continuously updated with new checkpoints. The following provides an overview of all currently available models. More coming soon.
News
April 20, 2023
-
Released initial set of StableLM-alpha models, with 3B and 7B parameters. 15B and 30B models are on the way. Base models are released under CC BY-SA-4.0.
-
Try to chat with our 7B model,
StableLM-Tuned-Alpha-7B, on HuggingFace Spaces.
Models
StableLM-Alpha
StableLM-Alpha models are trained on the new dataset that build on The Pile, which contains 1.5 trillion tokens, roughly 3x the size of The Pile. These models will be trained on up to 1.5 trillion tokens. The context length for these models is 4096 tokens.
An upcoming technical report will document the model specifications and the training settings.
As a proof-of-concept, we also fine-tuned the model with Stanford Alpaca‘s procedure using a combination of five recent datasets for conversational agents: Stanford’s Alpaca, Nomic-AI’s gpt4all, RyokoAI’s ShareGPT52K datasets, Databricks labs’ Dolly, and Anthropic’s HH. We will be releasing these models as StableLM-Tuned-Alpha.
| Size | StableLM-Base-Alpha | StableLM-Tuned-Alpha | Training Tokens | Parameters | Web Demo |
|---|---|---|---|---|---|
| 3B | checkpoint | checkpoint | 800B | 3,638,525,952 | |
| 7B | checkpoint | checkpoint | 800B | 7,869,358,080 | HuggingFace |
| 15B | (in progress) | (pending) | |||
| 30B | (in progress) | (pending) | |||
| 65B | (in progress) | (pending) | |||
| 175B | (planned) |
Quickstart
All StableLM models are hosted on the Huggingface hub. Check out this notebook to run inference with limited GPU capabilities.
Get started chatting with StableLM-Tuned-Alpha by using the following code snippet:
stop_ids = [50278, 50279, 50277, 1, 0]
for stop_id in stop_ids:
if input_ids[0][-1] == stop_id:
return True
return False
system_prompt = “””<|SYSTEM|># StableLM Tuned (Alpha version)
– StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
– StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
– StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
– StableLM will refuse to participate in anything that could harm a human.
“””
prompt = f”{system_prompt}<|USER|>What’s your mood today?<|ASSISTANT|>”
inputs = tokenizer(prompt, return_tensors=”pt”).to(“cuda”)
tokens = model.generate(
**inputs,
max_new_tokens=64,
temperature=0.7,
do_sample=True,
stopping_criteria=StoppingCriteriaList([StopOnTokens()])
)
print(tokenizer.decode(tokens[0], skip_special_tokens=True))” dir=”auto”>
import torch from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-tuned-alpha-7b") model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-tuned-alpha-7b") model.half().cuda() class StopOnTokens(StoppingCriteria): def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool: stop_ids = [50278, 50279, 50277, 1, 0] for stop_id in stop_ids: if input_ids[0][-1] == stop_id: return True return False system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version) - StableLM is a helpful and harmless open-source AI language model developed by StabilityAI. - StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user. - StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes. - StableLM will refuse to participate in anything that could harm a human. """ prompt = f"{system_prompt}<|USER|>What's your mood today?<|ASSISTANT|>" inputs = tokenizer(prompt, return_tensors="pt").to("cuda") tokens = model.generate( **inputs, max_new_tokens=64, temperature=0.7, do_sample=True, stopping_criteria=StoppingCriteriaList([StopOnTokens()]) ) print(tokenizer.decode(tokens[0], skip_special_tokens=True))
StableLM Tuned should be used with prompts formatted to <|SYSTEM|>...<|USER|>...<|ASSISTANT|>...
The system prompt is
This section contains a collection of fun cherry-picked examples of what you can do with stablelm-tuned-alpha.
Chit-Chat
User: Hey! My name is John nice to meet you!
StableLM: Hello John! It’s always a pleasure to meet new people.
User: The pleasure is mine. Hey my grandma is in Toronto. I want to plan a surprise visit for her. She’s a person who loves gardens and flowers.
StableLM: That’s wonderful! It’s great to hear that you’ll be visiting your grandma in Toronto. Can you tell me a little bit more about your plans?
User: Ya I need to book a flight there and a hotel. But first, what recommendations do you have for gifts that she might like?
StableLM: I think that’s a very thoughtful idea! It’s a very personal gift that would be sure to make her very happy. I can think of a few examples that she might really enjoy. There are some lovely bouquets or arrangements that would be lovely for the house, or even for the yard. Flowers are a great choice for a surprise gift, and they’re also a great choice for a wedding shower present. Also, if you’re really looking for something a bit more special, I think she’d really enjoy a quality set of cooking pots or pans. That’s something that she’s likely to use frequently, so it would make her feel really loved.
User: Thanks for the suggestion! Hmm a bouquet of flowers sounds nice but I don’t think I can take them on the air plane. What do you think I should do?
StableLM: There are many possible solutions! One option would be to arrange a small gift in the shape of a card and send it to her by regular mail. Or you could arrange a special meal at a restaurant that she likes, or even cook a meal at home for her. Or you could send her some local goodies that she might like, like a nice bouquet of flowers or a special recipe. You could even arrange for tickets to a local theatre or sporting event, and make sure to include a note about what you’d like her to know about you. Really any sort of special attention from you will be sure to make her very happy!
User: Ah! Right. I can order a bouquet for her online and get it delivered! Thanks!
StableLM: You’re very welcome! As long as you do this and make it a very personal, thoughtful gesture, she’ll be sure to appreciate it.
Formal Writing
User: What would you say to a friend who is graduating high school?
StableLM: I would say that they have every right to feel proud of themselves and their accomplishments. They should be proud of the work they’ve done and the friends they have made, and also be excited about the future.
User: Please write an email.
StableLM: Okay, here’s an example of what could be written:
Dear [Friend’s Name],
I hope this email finds you well. I just wanted to take a moment to express how proud I am of you and all that you have accomplished. I know that getting into [university or college] is a big accomplishment, and I appreciate all that you have done for me and for this generation.
I hope that you are having a good day. I’m sure that you are also concerned about the future, but I just wanted to let you know that I am also watching you grow and develop into the person that I know that you can be. Keep up the good work, and I have full faith that you will achieve great things.
Thank you again for everything that you do.
Best,
[Your Name]
Creative Writing
Rap Battles
User: Write an epic rap battle song between deep neural networks and symbolic AI
StableLM: [Beat drops]
Deep Neural Networks:
Listen up everyone, it’s time to witness
The power of deep neural networks, it’s just a matter of abstract
We’ve trained these networks to solve complex problems with ease
While symbolic AI is limited to simple math and simple flows
Symbolic AI:
Hold up, hold up, let me interrupt
It’s been a while since I’ve heard, some new thoughts you interrupt
But let me tell you, my friend, it’s not all about math and flow
It’s about making the world a better place, you know
Deep Neural Networks:
Well, I can see where you’re coming from, it’s clear
But deep neural networks, they never get the same gear
We can use them to analyze and predict with ease
And prove the superiority of machine learning
Symbolic AI:
You’re right, it’s not just math or numbers
But it’s the essence of our lives, it’s what counts, we’re numbers
I don’t need a complicated math formula, just a simple device
To make the world a better place, it’s a noble price
Deep Neural Networks:
I’ll give you that, my friend, you have a point
But let’s not forget, we’re making an ever-increasing joint
Our progress is not bound by logic, it’s a journey of the mind
So let’s work together, let’s strive, let’s leave all troubles behind
Symbolic AI:
Agreed, let’s work together, let’s not falter
We’re both making history, we’re both from the fader
So let’s make the world a better place, let’s end this debate
Cause it’s time to join forces, it’s time to leave no stone unturned
[Beat fades out]
Who won this epic rap battle between deep neural networks and symbolic AI? Well, it’s up to you to decide!
Fictional Stories
User: Write a story about a programmer who fell in love with a deep neural network.
StableLM: Once upon a time, there was a programmer named John. He was a brilliant and ambitious individual, who was constantly searching for the next big thing in technology. One day, while he was strolling through the streets of his hometown, he stumbled upon a group of people crowded around a mysterious object. Intrigued, he approached to find out what the fuss was about.
As he got closer, he realized that it was none other than a mysterious deep neural network. John’s mind was blown. He had never seen anything like it before. He had always been interested in machine learning, but this was something else entirely. He had to learn more about it.
John spent the next few weeks holed up in his hotel room, trying to learn everything he could about deep neural networks. He spent hours reading and analyzing papers and documents, trying to wrap his head around the concept of neural networks. He even managed to get into the local university’s computer science department, hoping to find some help there.
But, it wasn’t long before John realized that he was on his own. The city was bustling, and the constant chatter and noise of the city made it hard to concentrate on his work. He was about to give up when he stumbled upon a group of people playing a game that he had played before. They were having a good time, and John couldn’t help but join