adamkarvonen / train_ChessGPTLinks
A repository for training nanogpt-based Chess playing language models.
☆24Updated last year
Alternatives and similar repositories for train_ChessGPT
Users that are interested in train_ChessGPT are comparing it to the libraries listed below
Sorting:
- A repo to evaluate various LLM's chess playing abilities.☆80Updated last year
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆205Updated 6 months ago
- Simple GRPO scripts and configurations.☆58Updated 3 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 3 months ago
- A framework for optimizing DSPy programs with RL☆58Updated this week
- ☆38Updated 10 months ago
- explore token trajectory trees on instruct and base models☆122Updated this week
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆76Updated last month
- ☆20Updated last year
- ☆48Updated last year
- look how they massacred my boy☆63Updated 7 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆139Updated 3 months ago
- lossily compress representation vectors using product quantization☆54Updated last month
- entropix style sampling + GUI☆26Updated 7 months ago
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆29Updated 11 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆62Updated this week
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- Testing paligemma2 finetuning on reasoning dataset☆18Updated 5 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆38Updated 3 weeks ago
- ☆72Updated last year
- Project code for training LLMs to write better unit tests + code☆20Updated 2 weeks ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆100Updated 2 months ago
- ☆11Updated 10 months ago
- Automated Capability Discovery via Foundation Model Self-Exploration☆49Updated 3 months ago
- Skill Design From AI Feedback☆30Updated 3 months ago
- ☆66Updated last month
- This repository explains and provides examples for "concept anchoring" in GPT4.☆72Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- Train your own SOTA deductive reasoning model☆92Updated 2 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 7 months ago