furiousteabag / vram-calculator
Transformer GPU VRAM estimator
☆40Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for vram-calculator
- A tool that facilitates easy, efficient and high-quality fine-tuning of Cohere's models☆50Updated last week
- look how they massacred my boy☆58Updated last month
- Alice in Wonderland code base for experiments and raw experiments data☆109Updated last month
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆29Updated 6 months ago
- Jax like function transformation engine but micro, microjax☆26Updated 3 weeks ago
- ☆57Updated 11 months ago
- Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and min…☆23Updated last week
- Visualize expert firing frequencies across sentences in the Mixtral MoE model☆17Updated 10 months ago
- vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs☆89Updated this week
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆21Updated 5 months ago
- ☆48Updated last year
- Binary vector search example using Unum's USearch engine and pre-computed Wikipedia embeddings from Co:here and MixedBread☆19Updated 7 months ago
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆60Updated 6 months ago
- LLM training in simple, raw C/CUDA☆17Updated 6 months ago
- Training hybrid models for dummies.☆15Updated 3 weeks ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated last year
- ☆43Updated 4 months ago
- inference code for mixtral-8x7b-32kseqlen☆98Updated 11 months ago
- Simple examples using Argilla tools to build AI☆40Updated this week
- The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.☆38Updated 2 months ago
- ☆41Updated 2 weeks ago
- ☆22Updated last year
- Making the world's first and smartest opensource any-to-any AGI system☆26Updated this week
- RWKV-7: Surpassing GPT☆45Updated this week
- Public reports detailing responses to sets of prompts by Large Language Models.☆26Updated last year
- Make triton easier☆41Updated 5 months ago
- Because it's there.☆14Updated 2 months ago
- Run GreenBitAI's Quantized LLMs on Apple Devices with MLX☆15Updated this week