This collection lists all the historical (pre-"Hub") canonical model checkpoints, i.e. repos that were not under an org or user namespace
Julien Chaumond PRO
julien-c
AI & ML interests
<3 ML/AI for everyone, building products to propel communities fwd
Recent Activity
upvoted
an
article
34 minutes ago
What makes good reasoning data
upvoted
an
article
41 minutes ago
On the Shifting Global Compute Landscape
published
an
article
4 days ago
huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning
Organizations
[NB: Notes are from TuringPost]
-
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
Paper • 2403.09977 • Published • 11 -
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
Paper • 2403.14520 • Published • 35 -
SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
Paper • 2403.15360 • Published • 13
Papers cited in https://blog.vllm.ai/2024/07/25/lfai-perf.html
-
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
Paper • 2407.00079 • Published • 5 -
Llumnix: Dynamic Scheduling for Large Language Model Serving
Paper • 2406.03243 • Published -
CacheGen: Fast Context Loading for Language Model Applications
Paper • 2310.07240 • Published • 1 -
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Paper • 2405.04437 • Published • 3
referenced in the mergekit repo: https://github.com/cg123/mergekit
-
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper • 2203.05482 • Published • 7 -
Editing Models with Task Arithmetic
Paper • 2212.04089 • Published • 7 -
Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 15 -
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 30
Playing with git-theta: https://github.com/r-three/git-theta
This collection lists all the historical (pre-"Hub") canonical model checkpoints, i.e. repos that were not under an org or user namespace
referenced in the mergekit repo: https://github.com/cg123/mergekit
-
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper • 2203.05482 • Published • 7 -
Editing Models with Task Arithmetic
Paper • 2212.04089 • Published • 7 -
Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 15 -
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 30
[NB: Notes are from TuringPost]
-
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
Paper • 2403.09977 • Published • 11 -
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
Paper • 2403.14520 • Published • 35 -
SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
Paper • 2403.15360 • Published • 13
Playing with git-theta: https://github.com/r-three/git-theta
Papers cited in https://blog.vllm.ai/2024/07/25/lfai-perf.html
-
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
Paper • 2407.00079 • Published • 5 -
Llumnix: Dynamic Scheduling for Large Language Model Serving
Paper • 2406.03243 • Published -
CacheGen: Fast Context Loading for Language Model Applications
Paper • 2310.07240 • Published • 1 -
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Paper • 2405.04437 • Published • 3