Pinned Repositories
adept-inference-by-me
Inference code for Persimmon-8B
AgentGPT
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
copy_alibaba-lingjun-dataset-2023
fork_FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
lamma2-MP
A fork of FAIR's LLaMa, can do inference on 2 8GB GPU with out quantitate。 Easy to understand code changes.
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
LLaMa3-Numpy-trainable
用Numpy复现可训练的LLaMa3
PainlessInferenceAcceleration
platonic-rep-fock
从源代码中fock来的
template_IEEE_Journal
Lance729's Repositories
Lance729/template_IEEE_Journal
Lance729/AgentGPT
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
Lance729/adept-inference-by-me
Inference code for Persimmon-8B
Lance729/copy_alibaba-lingjun-dataset-2023
Lance729/fork_FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
Lance729/lamma2-MP
A fork of FAIR's LLaMa, can do inference on 2 8GB GPU with out quantitate。 Easy to understand code changes.
Lance729/llama3-from-scratch
llama3 implementation one matrix multiplication at a time
Lance729/LLaMa3-Numpy-trainable
用Numpy复现可训练的LLaMa3
Lance729/platonic-rep-fock
从源代码中fock来的
Lance729/Subspace-Tuning
来自上海交通大学的研究者们在对各种PEFT方法进行全面数学分析后，提出了一种新的框架——子空间微调，旨在将所有已知的PEFT方法统一在一个理论下，
Lance729/template-ieee-journal