KL3M
Click to visit website
About
KL3M is a family of language models that prioritizes clean training data, ensuring no copyright issues, toxicity, or synthetic data from other models. KL3M offers the Fairly Trained L Certification, which demonstrates compliance with content rights. The models excel in legal and financial contexts with minimal toxicity and bias. KL3M can be fine-tuned for various tasks, used as a pretrained checkpoint, or licensed for external use. Aimed at being efficient for real-world applications, KL3M already supports drafting invoices, contracts, and SEC filings among other tasks.
Platform
Task
Features
• high-quality content
• clean training data
• fairly trained l certification
• no copyright issues
• no toxicity
• pre-training and fine-tuning capabilities
• real-world task performance
• flexibility to license training data
FAQs
What kind of hardware do I need to run KL3M?
The first KL3M models have been designed with accessible use as a priority. kl3m-170 runs quickly on a MacBook Air M1, and kl3m-1.7b runs well on a $300 consumer GPU.
What architectures are your models?
Smaller KL3M models are trained using the GPT-NeoX architecture. Larger KL3M models are trained using the Mixtral Mixture-of-Experts architecture (trained from scratch).
How can I run KL3M?
KL3M is distributed as standard PyTorch model weights. KL3M architectures are supported for both HuggingFace transformers and vllm for inference.
Which languages are supported?
Larger models include content in English, Spanish (es-ES and es-MX), French, and German. We are working on adding more languages.
Do you provide an API?
Not yet. Our focus has been on enabling the use of small, local LLMs for information security and accessibility purposes, but we are evaluating the possibility of providing an API in the future.
Is it easy to fine-tune KL3M?
We have had excellent results fine-tuning KL3M on a number of use cases, including drafting, summarization, and classification. You can fine-tune kl3m-170 and kl3m-1.7b on consumer hardware.
How many tokens do you have?
We have collected over 2.5 trillion tokens of training data, and we are constantly adding more. Our training data is a mix of public domain and explicitly licensed content.
How many tokens have your models seen?
The smaller models have been trained on approximately 350B tokens of primarily English-language content. Larger models are being trained on between 500B to 1T tokens of content in English, Spanish, French, and German.
Do you have a conversational chat model?
Not yet. While our pretraining data does include a number of conversational sources, we have not yet trained a model that is designed for standard conversational rounds. Stay tuned.
Do you have a general instruction-aligned model?
Our base models already support a number of tasks like extractive/abstractive summarization or conversion, but we have not trained an open-ended model.
How do you pronounce KL3M?
KL3M is pronounced like "Clem" or "Klem."
Why is it named KL3M?
KL3M was originally short for the Kelvin Legal Large Language Model, KLLLM. Because we're nerds, we shortened all those Ls to L cubed or L, then shortened K-L-M to KL3M.
Average Rating: 0.0
Average Rating: 0.0
5 Stars:
0 Ratings
4 Stars:
0 Ratings
3 Stars:
0 Ratings
2 Stars:
0 Ratings
1 Star:
0 Ratings
User Ratings
No ratings available.
Sign In to Rate this Tool
Alternatives
Llama 3.2
The open-source AI model you can fine-tune and deploy, offering lightweight and multimodal capabilities.
View Details
PaLM-E
An embodied multimodal language model integrating real-world sensory data with language capabilities.
View Details
Google Gemma
Lightweight open language models by Google, optimized for various platforms and devices.
View Details
Mistral 7B
A powerful open-source LLM by Mistral AI, known for its performance and flexibility across various applications.
View Details
Llama LLM
An advanced open-source large language model by Meta, suitable for various applications.
View DetailsFeatured Tools
Sprunki Incredibox
Create spooky beats online with this unique musical game featuring character-based sound mixing.
View Details