Post
2508
BTW, in case anyone wants to kick the tires, test their 日本語, I have our Shisa V2 405B model up and running temporarily: https://chat.shisa.ai/
lhl PRO
leonardlin
AI & ML interests
None yet
Recent Activity
updated
a model
about 1 hour ago
shisa-ai/shisa-v2-llama3.1-405b-GGUF
liked
a model
about 8 hours ago
stockmark/Stockmark-2-VL-100B-beta
updated
a model
about 12 hours ago
shisa-ai/shisa-v2-llama3.1-405b-GGUF
Organizations
Articles
3
Article
62
An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct
Collections
25
-
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper • 2312.11514 • Published • 257 -
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
Paper • 2312.12456 • Published • 44 -
Accelerating LLM Inference with Staged Speculative Decoding
Paper • 2308.04623 • Published • 25 -
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
Paper • 2208.07339 • Published • 5
spaces
1
datasets
0
None public yet