arcee-ai / pybubbleLinks
☆70Updated 3 weeks ago
Alternatives and similar repositories for pybubble
Users that are interested in pybubble are comparing it to the libraries listed below
Sorting:
- ☆68Updated 6 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆99Updated 4 months ago
- Storing long contexts in tiny caches with self-study☆220Updated last week
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated last month
- look how they massacred my boy☆63Updated last year
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆84Updated 3 months ago
- Super basic implementation (gist-like) of RLMs with REPL environments.☆280Updated last month
- ☆29Updated last month
- SIMD quantization kernels☆93Updated 3 months ago
- Train your own SOTA deductive reasoning model☆107Updated 9 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆26Updated this week
- Simple & Scalable Pretraining for Neural Architecture Research☆304Updated last week
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated last year
- ☆40Updated last year
- lossily compress representation vectors using product quantization☆59Updated last month
- NSA Triton Kernels written with GPT5 and Opus 4.1☆66Updated 4 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 7 months ago
- A framework for optimizing DSPy programs with RL☆296Updated 3 weeks ago
- Project code for training LLMs to write better unit tests + code☆21Updated 6 months ago
- PageRank for LLMs☆51Updated 3 months ago
- An introduction to LLM Sampling☆79Updated last year
- Training-Ready RL Environments + Evals☆190Updated this week
- rl from zero pretrain, can it be done? yes.☆282Updated 2 months ago
- Benchmarks comparing PyTorch and MLX on Apple Silicon GPUs☆91Updated last year
- Efficient non-uniform quantization with GPTQ for GGUF☆56Updated 2 months ago
- Lego for GRPO☆30Updated 6 months ago
- explore token trajectory trees on instruct and base models☆149Updated 6 months ago
- Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic in…☆26Updated 6 months ago
- smolLM with Entropix sampler on pytorch☆149Updated last year
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆61Updated 7 months ago