Solar, a new bot created by Upstage, is now available on Poe. As a top-ranked model on the HuggingFace Open LLM leaderboard, and a fine tune of Llama 2, Solar is a great example of the progress enabled by open source. (1/3)
OPEN SOURCE
-
Superagent Deepdive Webinar on LLM Agent Platform
By
–
Superagent Deepdive Webinar Superagent by @pelaseyed is a platform for building, deploying, and managing LLM agents (built on top of LangChain/LangSmith) Join us for a webinar this Thursday to do a deep dive on all the technology behind it!
-
Create Your Own AutoTrain Space for No-Code Model Training
By
–
Create your own AutoTrain Space by clicking this link: https://
huggingface.co/new-space?temp
late=autotrain-projects/autotrain-advanced
… and start training models without writing any code! -
Integrating LLM inference in Lean via ONNX Runtime
By
–
Integrate Lean and LLM and an efficient way to run the inference in Lean. After training, the model is converted into the ONNX format, which can be run as a shared library using ONNX Runtime and integrated into Lean through FFI.
-
Meta Releases DINOv2 Training Code and Model Weights Under Apache-2
By
–
We've expanding access to DINOv2 by releasing the training code and model weights under the Apache-2 license.
— AI at Meta (@AIatMeta) 11 septembre 2023
Details on this and more of our recent work to advance computer vision research and fairness in AI ⬇️We've expanding access to DINOv2 by releasing the training code and model weights under the Apache-2 license. Details on this and more of our recent work to advance computer vision research and fairness in AI
-
Open Source Sustainability: Developer and Employer Responsibilities
By
–
Supply chain risk and open source sustainability: why the solution begins with developers but ends with their employers. The Flux example. By @mjasay for @InfoWorld https://
infoworld.com/article/370650
8/a-new-way-of-thinking-about-open-source-sustainability.html
… -
Fine-tune Llama 2 Physics Math Tasks Single T4 GPU
By
–
Very cool project from @ludwig_ai community member @TUNESHVERMA
—#finetune Llama 2 for physics + math tasks using just one T4 GPU with 4 bit quantization Notebook: https://
colab.research.google.com/drive/1RojNBnL
Ismm98sSNYAPC6d5WVVFX4tE9?usp=sharing
… Math Dataset: https://
pbase.ai/3raF8ga Physics Dataset: https://
pbase.ai/3r84fQC -
Create Your Own GPT with H2O GPT and LLM Studio
By
–
Join us for a webinar with @Rob_Mulla Grandmaster & Sr. Principal Data Scientist at @h2oai
! Learn to create your own GPT with #h2oGPT & H2O #LLMStudio. Register: https://
bit.ly/3PyhiEs -
DWPose: Two-Stage Distillation for Whole-Body Pose Estimation
By
–
IDEA-Research/DWPose: Official implementation of the paper "Effective Whole-body Pose Estimation with Two-stages Distillation" https://
bit.ly/43XZMgZ
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
ToolBench: Open Platform for LLM Tool Learning
By
–
OpenBMB/ToolBench: An open platform for training, serving, and evaluating large language model for tool learning. https://
bit.ly/3s0agPn