gitpulse

transformer

16 kho được công bố.

Kho
1
huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
169k +0.0%+0.2%+0.8% 58
2
vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs
97k +0.0%+0.4%+3.4% 71
3
labmlai/annotated_deep_learning_paper_implementations 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
67.8k -0.0%+0.0%+0.3% 30
4
ggml-org/whisper.cpp Port of OpenAI's Whisper model in C/C++
55.2k +0.0%+0.4%+1.6% 37
5
p-e-w/heretic Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
40.6k +0.2%+1.7%+15.5% 97
6
sgl-project/sglang SGLang is a high-performance serving framework for large language models and multimodal models.
38.9k +0.1%+0.8%+4.8% 37
7
33.7k +0.0%+0.3%+1.9% 30
8
SYSTRAN/faster-whisper Faster Whisper transcription with CTranslate2
26.8k +0.1%+0.7%+3.5% 19
9
lukasmasuch/best-of-ml-python 🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
23.9k -0.0%+0.0%+0.1% 11
10
nndl/nndl 邱锡鹏《神经网络与深度学习》第二版与通识版:电子书、章节目录、学习资源与勘误。
19.6k +0.0%+0.2%+1.0% 5
11
FlashML-org/FreeToken FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
17.2k +0.2%+2.3%+18.8% 146
12
datawhalechina/leedl-tutorial 《李宏毅深度学习教程》(李宏毅老师推荐👍,苹果书🍎),PDF下载地址:https://github.com/datawhalechina/leedl-tutorial/releases
16.9k +0.0%+0.1%+0.4% 6
13
alibaba/MNN MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
16.5k +0.0%+0.6%+1.9% 6
14
BlinkDL/RWKV-LM RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
14.8k -0.0%+0.0%+0.1% 8
15
EleutherAI/lm-evaluation-harness A framework for few-shot evaluation of language models.
14.5k +0.1%+0.3%+1.8% 6
16
FareedKhan-dev/kimi-k3-in-c A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
12.1k +0.6%+7.4%+34.0% 114