Cut Your Losses in Large-Vocabulary Language Models
Paper
•
2411.09009
•
Published
•
38
Trolle Karlsson PRO
trollek
AI & ML interests
Stable Diffusion and small language models, but I'm a curious fella.
Recent Activity
Reacted to
cfahlgren1's
post
with ❤️
about 9 hours ago
observers 🔭 - automatically log all OpenAI compatible requests to a dataset💽
• supports any OpenAI compatible endpoint 💪
• supports DuckDB, Hugging Face Datasets, and Argilla as stores
> pip install observers
No complex framework. Just a few lines of code to start sending your traces somewhere. Let us know what you think! @davidberenstein1957 and I will continue iterating!
Here's an example dataset that was logged to Hugging Face from Ollama: https://huggingface.co/datasets/cfahlgren1/llama-3.1-awesome-chatgpt-prompts
upvoted
a
paper
7 days ago
Cut Your Losses in Large-Vocabulary Language Models
liked
a model
10 days ago
ZeroXClem/Qwen2.5-7B-Qandora-CySec
Organizations
None yet
trollek's activity
upvoted
a
paper
7 days ago
upvoted
a
paper
4 months ago
upvoted
an
article
5 months ago
Article
Uncensor any LLM with abliteration
By
•
•
370
upvoted
an
article
6 months ago
Article
⚗️ 🔥 Building High-Quality Datasets with distilabel and Prometheus 2
By
•
•
26
upvoted
a
paper
7 months ago
upvoted
an
article
7 months ago
Article
GaLore: Advancing Large Model Training on Consumer-grade Hardware
•
25
upvoted
3
papers
8 months ago