|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
tags: |
|
- function calling |
|
- mistral |
|
- llama |
|
- open source ai |
|
- code |
|
- task automation |
|
- workflow automation |
|
library_name: nemo |
|
pipeline_tag: conversational |
|
--- |
|
|
|
# Atom |
|
|
|
a suite of finetuned LLMs for atomically precise function calling 🧪 |
|
|
|
✅ Massive function calling dataset of over 20M samples. |
|
|
|
✅ First Model: Atom-Z-Tiny - Zephr trained on 100k samples |
|
|
|
✅ Vision function calling coming soon |
|
|
|
## Usage |
|
|
|
```python |
|
import torch |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("kye/Atom-Z-Tiny-7B") |
|
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
"kye/Atom-Z-Tiny-7B", |
|
trust_remote_code=True, |
|
).to(device) |
|
|
|
task = """ |
|
|
|
|
|
[INST] <<SYS>> |
|
<function>Available functions: |
|
<function>{ |
|
"name": "generate_password", |
|
"description": "Generate a random password with specified criteria", |
|
"parameters": { |
|
"type": "object", |
|
"properties": { |
|
"length": { |
|
"type": "integer", |
|
"description": "The length of the password" |
|
}, |
|
"include_numbers": { |
|
"type": "boolean", |
|
"description": "Include numbers in the password" |
|
}, |
|
"include_special_characters": { |
|
"type": "boolean", |
|
"description": "Include special characters in the password" |
|
} |
|
}, |
|
"required": [ |
|
"length" |
|
] |
|
} |
|
} |
|
<</SYS>> |
|
|
|
I need a new password. Can you generate one for me? [/INST] |
|
|
|
|
|
""" |
|
|
|
input_ids = tokenizer.encode(task, return_tensors="pt") |
|
output = model.generate(input_ids.to(device), max_length=128, temperature=0.7).cpu() |
|
output_text = tokenizer.decode(output[0], skip_special_tokens=True) |
|
print(output_text) |
|
|
|
|
|
``` |
|
|
|
|
|
# Contribute |
|
To contribute please join the Agora discord: |
|
|
|
https://discord.gg/dMPPswVcZ8 |
|
|
|
All of our operations take place here and you can learn how to contribute to models that advance Humanity! |
|
|
|
We're also granting GPU power to researchers working on cool projects so share your project! |
