bloomberg/minilmv2.bb
Our open source implementation of MiniLMv2 (https://aclanthology.org/2021.findings-acl.188)
This project helps machine learning engineers and researchers reduce the size and computational cost of large language models while maintaining their performance. It takes pre-trained large language models (teacher models) and the data they were trained on as input. The output is a smaller, more efficient 'student' language model that can be deployed more easily.
No commits in the last 6 months.
Use this if you need to deploy powerful transformer-based language models in resource-constrained environments or accelerate inference times for natural language processing tasks.
Not ideal if you are looking for a pre-trained, ready-to-use small language model without needing to perform a distillation process yourself.
Stars
61
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/bloomberg/minilmv2.bb"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
facebookresearch/LayerSkip
Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
FareedKhan-dev/train-llm-from-scratch
A straightforward method for training your LLM, from downloading data to generating text.
kmeng01/rome
Locating and editing factual associations in GPT (NeurIPS 2022)
datawhalechina/llms-from-scratch-cn
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理