Sakana AI has announced Evolutionary Model Merge, a technique that automates and advances model merging. Models and demos using this method have been released. Give them a try!
OPEN SOURCE
-
LangGraph Agent Supervisor with Anthropic Models Open-Sourced
By
–
Agent Supervisor with Anthropic We've put a lot of work into LangGraph to make it the best run time for agents. Most of the examples are with OpenAI, but @eucheetan just open-sourced an example with @AnthropicAI models https://
github.com/prof-frink-lab
/slangchain/blob/main/docs/modules/graphs/examples/anthropic/agent_supervisor.ipynb
… -
DROID: Large-Scale Open-Source Robot Manipulation Dataset
By
–
9/ DROID
— DAIR.AI (@dair_ai) 24 mars 2024
An open-source, large-scale robot manipulation dataset to train and build more capable and robust robotic manipulation policies; it contains 76K demonstration trajectories, collected across 564 scenes and 86 tasks.https://t.co/8xAIyepZ0u9/ DROID An open-source, large-scale robot manipulation dataset to train and build more capable and robust robotic manipulation policies; it contains 76K demonstration trajectories, collected across 564 scenes and 86 tasks.
-
Agent-FLAN: Fine-tuning Language Models for Enhanced Agent Performance
By
–
7/ Agent-FLAN Designs data and methods to effectively fine-tune language models for agents, referred to as Agent-FLAN; this enables Llama2-7B to outperform prior best works by 3.5% across various agent evaluation datasets.
-
LLM4Decompile: Open-Source Decompilation Models Up to 33B
By
–
6/ LLM4Decompile A family of open-access decompilation LLMs ranging from 1B to 33B parameters; these models are trained on 4 billion tokens of C source code and corresponding assembly code.
-
Evolutionary Model Merge: Automating Foundation Model Development
By
–
2/ Evolutionary Model Merge
— DAIR.AI (@dair_ai) 24 mars 2024
An approach for automating foundation model development using evolution to combine open-source models; facilitates cross-domain merging where a Japanese Math LLM achieved SOTA performance on Japanese LLM benchmarks.https://t.co/0pFqLGg0EY2/ Evolutionary Model Merge An approach for automating foundation model development using evolution to combine open-source models; facilitates cross-domain merging where a Japanese Math LLM achieved SOTA performance on Japanese LLM benchmarks.
-
Implemented Neural Networks Projects and Applied Machine Learning Repository
By
–
Implemented #NeuralNetworks Projects: https://
medium.com/coders-mojo/im
plemented-neural-networks-projects-d25a6476d72b
… compiled by @NainaChaturved8 ————
#DataScience #DataScientists #AI #Coding #Python #MachineLearning #DeepLearning ————
Also see below the repository of 60+ implemented Applied ML Projects with code… -
Fine-tune Mistral-7B with synthetic prompt-response datasets
By
–
Switch all prompts to mistral-large. Run the repo many times, collect the prompts / responses for each input / output. Format as JSONL, train a Mistral-7B or similar on all of them, and slot it in.
-
Fine-tuning AI models in 10 minutes with Runpod
By
–
10 minutes? Pretty doable actually, if the data is ready. Spin up a Runpod machine. While that’s starting, upload dataset to huggingface. Then write a yaml for the run config (Axolotl) and upload to Gist. By that time the machine is ready. Run this command: pip uninstall -y
-
Axolotl and Mistral for Synthetic Data Generation
By
–
Axolotl. Fucking awesome. Shoutout to @winglian
. For synthetic data, Mistral models are great. Pair that with some real-world data for grounding/diversity/inspiration for good results. @csahil28 is building an even better solution here. Costs depend on the task at hand. Can be