@mattshumer_

–

27 March 2024 17h01

You can go from an idea to a fully trained model in a matter of minutes. And the resulting models are really capable!

claude-llm-trainer: AI Model Training Platform Using Claude 3

By

–

27 March 2024 17h01

How it works: – The user describes the model they want
Ex: "A model that writes Python functions" – claude-llm-trainer leverages a chain of Claude 3 calls to create a great dataset for your task. – We process the dataset, and train a LLaMA model!

Claude LLM Trainer: Open-Source Task-Specific Model Training

By

–

27 March 2024 17h01

Introducing `claude-llm-trainer` ✍️

The world's simplest way to train a task-specific LLM.

Just write a sentence describing the model you want.

A chain of AI systems will generate a dataset and train a model for you.

And it's open-source. pic.twitter.com/k6NDkSMmcB
— Matt Shumer (@mattshumer_) 27 mars 2024

Introducing `claude-llm-trainer` The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

DBRX Model Uses GPT-4 Tokenizer for Improved Efficiency

By

–

27 March 2024 16h36

One of the more interesting things about the new DBRX model is it uses the GPT-4 tokenizer. Compared to the LLaMA tokenizer (used by Mixtral), it's ~20% more efficient. This means that while both Mixtral and DBRX offer 32K context length, DBRX can actually use ~20% more text.

Databricks New LLM Beats Mixtral in Open-Source Race

By

–

27 March 2024 16h15

There's a new king of open-source. The new LLM from @databricks just beat Mixtral! – 132B total params (16 experts), 36B active (4 experts)
– Trained on *12T* tokens
– 32K context length From my initial tests, I'm really impressed.

Further Training Could Enhance AI Capabilities

By

–

27 March 2024 7h30

I dunno, with some further training there’s a shot it ends up pretty capable

AI Speeds Up Development: Building Fast with Automation

By

–

27 March 2024 7h30

Lots of reps over time has taught me to build fast. AI helps. I spend maybe 5% of my day on these sorts of projects. And no, not at all. HyperWrite is my main focus.