tomekkorbak / bliss-attractorsLinks
A toy Inspect implementation of the Bliss Attractor eval from Claude 4 System Card Welfare Assessment
☆33Updated 3 months ago
Alternatives and similar repositories for bliss-attractors
Users that are interested in bliss-attractors are comparing it to the libraries listed below
Sorting:
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated 10 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 6 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated 10 months ago
- look how they massacred my boy☆64Updated 11 months ago
- ☆45Updated 3 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated 11 months ago
- Lego for GRPO☆29Updated 3 months ago
- Plotting (entropy, varentropy) for small LMs☆99Updated 4 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆83Updated last month
- Marketplace ML experiment - training without backprop☆25Updated 2 weeks ago
- smolLM with Entropix sampler on pytorch☆150Updated 10 months ago
- explore token trajectory trees on instruct and base models☆133Updated 3 months ago
- Moondream MCP Server in Python☆41Updated 2 months ago
- ☆68Updated 4 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆71Updated 5 months ago
- ☆13Updated 5 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 7 months ago
- Approximating the joint distribution of language models via MCTS☆21Updated 10 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 6 months ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆74Updated 7 months ago
- train entropix like a champ!☆20Updated 11 months ago
- ☆63Updated last month
- Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLM…☆73Updated 3 weeks ago
- ☆14Updated 5 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago
- An introduction to LLM Sampling☆79Updated 9 months ago
- Train your own SOTA deductive reasoning model☆106Updated 6 months ago
- The next evolution of Agents☆47Updated this week
- A graph visualization of attention☆57Updated 4 months ago