advait / c4a0Links
Alpha-Zero Connect Four NN trained via self play
☆19Updated 3 months ago
Alternatives and similar repositories for c4a0
Users that are interested in c4a0 are comparing it to the libraries listed below
Sorting:
- Latent Large Language Models☆18Updated 10 months ago
- ☆18Updated last year
- ☆38Updated 11 months ago
- Because it's there.☆16Updated 9 months ago
- Simple repository for training small reasoning models☆33Updated 4 months ago
- Fast reinforcement learning 💨☆24Updated 3 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago
- Testing paligemma2 finetuning on reasoning dataset☆18Updated 5 months ago
- alternative way to calculating self attention☆18Updated last year
- coloring terminal text with intensities (used for plotting probability, entropy with tokens)☆12Updated 8 months ago
- ☆20Updated 3 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆66Updated 2 months ago
- Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and min…☆26Updated 7 months ago
- ☆21Updated last month
- ☆39Updated last month
- Jax like function transformation engine but micro, microjax☆32Updated 8 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 4 months ago
- ☆23Updated 8 months ago
- ☆27Updated 11 months ago
- ☆23Updated 6 months ago
- Lego for GRPO☆28Updated last month
- ☆10Updated 2 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated 4 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated 3 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆21Updated 11 months ago
- Nexusflow function call, tool use, and agent benchmarks.☆20Updated 6 months ago
- NanoGPT (124M) in 5 minutes☆11Updated 4 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆82Updated 3 weeks ago
- Training AI for Super Smash Bros. Melee☆27Updated 3 months ago
- rl from zero pretrain, can it be done? we'll see.☆56Updated this week