DolbyUUU / DeepEnlightenLinks
Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.
☆38Updated 8 months ago
Alternatives and similar repositories for DeepEnlighten
Users that are interested in DeepEnlighten are comparing it to the libraries listed below
Sorting:
- The code for paper "Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review" accepted by ACL 2025.☆103Updated 6 months ago
- ☆210Updated last month
- ☆104Updated last month
- Chicago Project☆51Updated 6 months ago
- ☆162Updated 7 months ago
- PMSX003(PMS1003, PMS3003, PMS5003, PMS6003, PMS7003, PMS9003M, PMSA003) full-featured driver library for general-purpose MCU and Linux.☆99Updated 3 weeks ago
- ☆105Updated 2 months ago
- ☆80Updated 2 weeks ago
- ☆161Updated last month
- ☆156Updated 3 months ago
- ☆110Updated 8 months ago
- ☆101Updated 7 months ago
- Use the trained model to predict if a patient has heart disease☆32Updated 9 months ago
- semqreg package☆120Updated 3 months ago
- ☆204Updated last year
- Go bindings for the CUDA Driver and Runtime APIs, cuBLAS, and cuDNN.☆154Updated last month
- Building a Q&A LLM Agent to Answer Questions about Your Dataset☆103Updated 7 months ago
- Fast Hierarchical Dart Throwing (HDT) implementation for generating 2D Poisson Disk blue noise distributions, written in Rust with Python…☆81Updated 6 months ago
- BERT-based AI-generated academic text detection model☆205Updated 3 weeks ago
- Workflow runner engine for argo framework☆99Updated 9 months ago
- 借鉴一下大佬的思路,少部分原创☆71Updated 6 months ago
- MAX31855 full-featured driver library for general-purpose MCU and Linux.☆70Updated 3 weeks ago
- Evolve-AI☆40Updated 9 months ago
- Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)☆41Updated 9 months ago
- An configuration provider that enables configuration binding via attributes in Microsoft.Extensions.Configuration.☆85Updated 5 months ago
- BEACON☆40Updated 9 months ago
- A gRPC framework for Go that provides out-of-the-box gRPC service development experience.☆80Updated last month
- TikTok emojis component library monorepo. Contains React and Vue 3 packages with 46 secret TikTok emojis (smile, happy, angry, etc.) usin…☆202Updated 3 months ago
- 用Java编写一个ai智能体,从0完整实现一个Claude Code☆51Updated 3 weeks ago
- ☆100Updated 10 months ago