Coconut Files

Training Large Language Model to Reason in a Continuous Latent Space

This is an exact mirror of the Coconut project, hosted at https://github.com/facebookresearch/coconut. SourceForge is not affiliated with Coconut.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
coconut source code.tar.gz	2025-08-12	5.5 MB	0
coconut source code.zip	2025-08-12	5.5 MB	2
Totals: 2 Items		11.0 MB	2

Other Useful Business Software

Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.

Start Free

Paessler - Monitor Your Whole Network in Minutes

Auto-discovery finds your devices and deploys pre-configured sensors instantly. No project plan required, just visibility from day one.

Waiting weeks for a monitoring rollout isn't an option when infrastructure doesn't stop running. PRTG's auto-discovery scans your network and suggests from over 200 pre-configured sensor types, so you're watching servers, applications and devices within minutes, not after a multi-week deployment. Enterprise-strength monitoring, without the enterprise complexity. Start your free trial today.

Start Free 30-Day Trial

Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Start Free

Recommended Projects

Alpaca-CoT
We unified the interfaces of instruction-tuning data
DecryptPrompt
Summarize Prompt & LLM papers, open source data & models
$Qwen2.5-Math$

Qwen2.5-Math
A series of math-specific large language models of our Qwen2 series
GibbsLDA++: A C/C++ Gibbs Sampling LDA
GibbsLDA++: A C/C++ Implementation of Latent Dirichlet Allocation (LDA) using Gibbs Sampling for parameter estimation and inference. GibbsLDA++ is fast and is designed to analyze hidden/latent topic structures of large-scale (text) data collections.
DeepSDF
Learning Continuous Signed Distance Functions for Shape Representation