-
yuzhaouoe.github.io Public
Forked from alessiodevoto/alessiodevoto.github.ioJavaScript UpdatedJun 4, 2025 -
vllm Public
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Python Apache License 2.0 UpdatedMay 26, 2025 -
Magma Public
Forked from microsoft/Magma[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
Python MIT License UpdatedMay 9, 2025 -
l2compress Public
Forked from alessiodevoto/l2compressA simple and effective L2 norm based method for KV Cache compression.
Python UpdatedJan 9, 2025 -
[NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
-
awesome-hallucination-detection Public
Forked from EdinburghNLP/awesome-hallucination-detectionList of papers on hallucination detection in LLMs.
Apache License 2.0 UpdatedNov 1, 2024 -
sae Public
Forked from EleutherAI/sparsifySparse autoencoders
Python MIT License UpdatedAug 26, 2024 -
YaFSDP Public
Forked from yandex/YaFSDPYaFSDP: Yet another Fully Sharded Data Parallel
Python Apache License 2.0 UpdatedAug 19, 2024 -
pretraining-data-packing Public
[ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training
-
LongLoRA Public
Forked from dvlab-research/LongLoRACode and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
Python Apache License 2.0 UpdatedJun 2, 2024 -
LLMTest_NeedleInAHaystack Public
Forked from gkamradt/LLMTest_NeedleInAHaystackDoing simple retrieval from LLM models at various context lengths to measure accuracy
Jupyter Notebook Other UpdatedMay 10, 2024 -
rome Public
Forked from kmeng01/romeLocating and editing factual associations in GPT (NeurIPS 2022)
Python MIT License UpdatedApr 20, 2024 -
inseq Public
Forked from inseq-team/inseqInterpretability for sequence generation models 🐛 🔍
Python Apache License 2.0 UpdatedApr 15, 2024 -
-
massive-activations Public
Forked from locuslab/massive-activationsCode accompanying the paper "Massive Activations in Large Language Models"
Python MIT License UpdatedMar 4, 2024
{{ message }}