antirez / LLM-FTC-samplingLinks
First token cutoff sampling inference example
☆30Updated 2 years ago
Alternatives and similar repositories for LLM-FTC-sampling
Users that are interested in LLM-FTC-sampling are comparing it to the libraries listed below
Sorting:
- Benchmarks comparing PyTorch and MLX on Apple Silicon GPUs☆93Updated 2 weeks ago
- Because it's there.☆16Updated last year
- The official evaluation suite and dynamic data release for MixEval.☆11Updated last year
- Transformer GPU VRAM estimator☆68Updated last year
- The Engineer's Guide to Deep-Learning☆36Updated last year
- Aana SDK is a powerful framework for building AI enabled multimodal applications.☆55Updated 5 months ago
- Tooling for exact and MinHash deduplication of large-scale text datasets☆65Updated 3 weeks ago
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆58Updated last year
- Training hybrid models for dummies.☆29Updated 3 months ago
- Like picoGPT but for BERT.☆51Updated 2 years ago
- C API for MLX☆172Updated this week
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated 2 years ago
- Public repository containing METR's DVC pipeline for eval data analysis☆199Updated last week
- Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp☆14Updated 11 months ago
- ☆21Updated last year
- ☆44Updated this week
- A Learning Journey: Micrograd in Mojo 🔥☆65Updated last year
- Pivotal Token Search☆144Updated last month
- Real-time visualisation☆21Updated 4 months ago
- GGUF implementation in C as a library and a tools CLI program☆303Updated 5 months ago
- 🛠 Self-hosted, fast, and consistent remote configuration for apps.☆17Updated 3 years ago
- run embeddings in MLX☆97Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 3 months ago
- ☆15Updated 7 months ago
- A minimalistic C++ Jinja templating engine for LLM chat templates☆203Updated 4 months ago
- Using modal.com to process FineWeb-edu data☆20Updated 10 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 last year
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆61Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 4 months ago
- ☆12Updated last year