tanmaysachan / splitcomputeLinks
Split model weights and execute partially
☆4Updated 11 months ago
Alternatives and similar repositories for splitcompute
Users that are interested in splitcompute are comparing it to the libraries listed below
Sorting:
- Because it's there.☆16Updated 9 months ago
- Stream of my favorite papers and links☆41Updated 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
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆82Updated 3 weeks ago
- Compiling useful links, papers, benchmarks, ideas, etc.☆46Updated 3 months ago
- ☆38Updated 11 months ago
- Simple repository for training small reasoning models☆33Updated 4 months ago
- ☆20Updated 3 months ago
- Verbosity control for AI agents☆63Updated last year
- look how they massacred my boy☆63Updated 8 months ago
- SIMD quantization kernels☆72Updated this week
- Sphynx Hallucination Induction☆54Updated 4 months ago
- Modded vLLM to run pipeline parallelism over public networks☆37Updated last month
- A miniature version of Modal☆20Updated last year
- ☆63Updated last month
- coloring terminal text with intensities (used for plotting probability, entropy with tokens)☆12Updated 8 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆41Updated last month
- in this repository, i'm going to implement increasingly complex llm inference optimizations☆60Updated last month
- Using modal.com to process FineWeb-edu data☆20Updated 2 months ago
- ☆47Updated last year
- Approximating the joint distribution of language models via MCTS☆21Updated 7 months ago
- An introduction to LLM Sampling☆78Updated 6 months ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- PageRank for LLMs☆42Updated 2 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆95Updated last month
- rl from zero pretrain, can it be done? we'll see.☆56Updated this week
- Training code for Sparse Autoencoders on Embedding models☆38Updated 4 months ago
- lossily compress representation vectors using product quantization☆57Updated 2 months ago
- ☆30Updated 7 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago