An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
-
Updated
May 11, 2024 - Python
An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Unify Efficient Fine-Tuning of 100+ LLMs
Implementation for the different ML tasks on Kaggle platform with GPUs.
算法岗-自然语言处理-大语言模型-应试资料
IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT
Discrete Bayesian optimization with LLMs, PEFT finetuning methods, and the Laplace approximation.
Firefly: 大模型训练工具,支持训练Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
This repository is dedicated to small projects and some theoretical material that I used to get into NLP and LLM in a practical and efficient way.
Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning
Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"
Finetune mistral-7b-instruct for sentence embeddings
Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting
LLM Finetuning with peft
Easy and Efficient Finetuning of QLoRA LLMs. (Supported LLama, LLama2, bloom, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.
Demonstration of LLM techniques such as prompt engineering, full finetuning, PEFT (LoRA) etc.
Thesis scope: Train and Develop a Table-to-Text Transformer-based model for contextual summarization of tabular data. To achieve this T5-small , T5-base, Bart-base and Llama2 7B chat were finetuned on ToTTo and QTSumm. Regarding ToTTo, the models outperformed the benchmark.
Genie in the Box: Distill Whisper STT => Mistral-7B => Phind/Phind-CodeLlama-34B-v2 => GPT 3.5 => Coqui's TTS/OpenAI TTS
Add a description, image, and links to the peft topic page so that developers can more easily learn about it.
To associate your repository with the peft topic, visit your repo's landing page and select "manage topics."