InternLM/Spark
An official implementation of "SPARK: Synergistic Policy And Reward Co-Evolving Framework"
SPARK helps AI researchers and developers fine-tune large language models more efficiently. It takes in existing language models and automatically generates both the policy (how the model behaves) and the reward signals (how well it performs) from verifiable data, leading to a self-learning and self-evolving system. The output is a more capable, specialized language model that can perform better on various tasks.
Use this if you are a researcher or AI engineer looking to enhance large language models by integrating policy and reward mechanisms within a single model for joint training, without needing human preference data or external reward models.
Not ideal if you are a general user looking for an off-the-shelf AI tool for everyday tasks, as this is a framework for advanced model training and development.
Stars
25
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/InternLM/Spark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.