PrimeIntellect-ai / primeLinks
Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrastructure for AI development at scale.
☆121Updated this week
Alternatives and similar repositories for prime
Users that are interested in prime are comparing it to the libraries listed below
Sorting:
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆77Updated 10 months ago
- Curated collection of community environments☆195Updated last week
- Plotting (entropy, varentropy) for small LMs☆99Updated 7 months ago
- SIMD quantization kernels☆93Updated 3 months ago
- look how they massacred my boy☆63Updated last year
- ☆90Updated 11 months ago
- peer-to-peer compute and intelligence network that enables decentralized AI development at scale☆135Updated last month
- TOPLOC: is a novel method for verifiable inference that enables users to verify that LLM providers are using the correct model configurat…☆50Updated 8 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated last year
- Super basic implementation (gist-like) of RLMs with REPL environments.☆286Updated 2 months ago
- Serverless Posttraining☆65Updated this week
- ☆136Updated 9 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆84Updated 4 months ago
- ☆141Updated last week
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆58Updated last year
- Modded vLLM to run pipeline parallelism over public networks☆41Updated 7 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated last year
- Train your own SOTA deductive reasoning model☆107Updated 9 months ago
- EXO Gym is an open-source Python toolkit that facilitates distributed AI research.☆88Updated 3 weeks ago
- explore token trajectory trees on instruct and base models☆149Updated 6 months ago
- train entropix like a champ!☆20Updated last year
- ☆68Updated 7 months ago
- The State Of The Art, intelligence☆157Updated 4 months ago
- ☆14Updated 8 months ago
- Letting Claude Code develop his own MCP tools :)☆122Updated 9 months ago
- Marketplace ML experiment - training without backprop☆27Updated 3 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆99Updated 5 months ago
- Automated Capability Discovery via Foundation Model Self-Exploration☆65Updated 10 months ago
- Repository to create traveling waves integrate special information through time☆56Updated 4 months ago
- Claude Deep Research config for Claude Code.☆224Updated 9 months ago