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
Mistral 7B
A powerful open-source LLM by Mistral AI, known for its performance and flexibility across various applications.
View DetailsLlama LLM
State-of-the-art open-source language model by Meta with 8B and 70B parameters for diverse applications.
View DetailsNeuryte AI
A privacy-first local large language model (LLLM) for fast and secure tasks including chat and code completions.
View DetailsRelated Tools
Flip AI
Predict and resolve business disruptions using an LLM specifically designed for DevOps.
View DetailsMK1 Flywheel
World's most performant LLM Inference Engine for secure, high-speed AI workloads.
View DetailsKern AI
Enhance LLM reliability through advanced data modeling and integration for trustworthy AI solutions.
View DetailsEyeLevel AI
Transform documents into LLM-ready data and reduce AI hallucinations with EyeLevel's APIs and no-code tools.
View DetailsTrojan Detection Challenge 2023
A NeurIPS 2023 competition focused on detecting hidden functions in large language models.
View DetailsFeatured Tools
TiramAi
Create user personas and user stories quickly with TiramAi's AI-powered solutions.
View DetailsDezyn
Interactive architectural diagram tool with AI-powered features for flowcharts and cloud architectures.
View DetailsSayIntentions.AI
The Future of AI for Aviation Simulation. Experience Immersion Like Never Before! - AI Air Traffic Control - AI CabinCrews - AI TourGuides - AI Mentors
View DetailsAI Math Solver
A powerful AI tool for solving complex math problems with step-by-step explanations and support for photo upload.
View DetailsSherloq
A collaborative SQL management platform for data teams, enabling efficient query sharing and organization.
View DetailsAutoKT
Automate and enhance your documentation with AI-driven solutions for knowledge transfer.
View Details