-
serendipity expert
- Rome, Italy
- http://www.seralf.it
- @seralf
Highlights
- Pro
Block or Report
Block or report seralf
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseLists (1)
Sort Name ascending (A-Z)
Stars
Language
Sort by: Recently starred
Modelli dati semantici ISPRA (ontologie, vocabolari controllati, schemi)
Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.
The Persistence of Vision Raytracer: http://www.povray.org/
Keras Callback to Automatically Adjust the learning rate when it stops improving
Textual analytics experiments to help extract value from unstructured text data
Inference Llama 2 in Scala with AVX2 kernels in C (A port of llama2.c from Andrej Karpathy)
JS tokenizer for LLaMA 1 and 2
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
A holistic way of understanding how LLaMA and its components run in practice, with code and detailed documentation.
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
speedup for lm-evaluation-harness; support tensor-parallel inference and data-parallel inference; support gptq, bitsandbytes, peft and exllamav2.
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
FUSE-based file system backed by Amazon S3
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
Open, Multi-modal Catalog for Data & AI
How to evaluate the Quality of your Data with Great Expectations and Spark.
Graph Machine Learning course, Xavier Bresson, 2023
Data Engineering with Scala, published by Packt