Anima
FastLoRAChat
Anima | FastLoRAChat | |
---|---|---|
3 | 2 | |
2,881 | 119 | |
- | - | |
9.1 | 7.2 | |
13 days ago | about 1 year ago | |
Jupyter Notebook | Jupyter Notebook | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Anima
- AirLLM
- AirLLM enables 8GB MacBook run 70B LLM
-
Fitting 70B models in a 4gb GPU, The whole model, no quants or distil or anything!
Found out about air_llm, https://github.com/lyogavin/Anima/tree/main/air_llm, where it loads one layer at a time, allow each layer to be 1.6GB for a 70b with 80 layers. theres about 30mb for kv cache, and i'm not sure where the rest goes.
FastLoRAChat
-
[P] FastLoRAChat Instruct-tune LLaMA on consumer hardware with shareGPT data
Announcing FastLoRAChat , training chatGPT without A100.
- FastLoRAChat – Lora finetuned LLM with ChatGPT capabality
What are some alternatives?
Local-LLM-Langchain - Load local LLMs effortlessly in a Jupyter notebook for testing purposes alongside Langchain or other agents. Contains Oobagooga and KoboldAI versions of the langchain notebooks with examples.
ragas - Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
fin-llama - LLAMA specialized on finance
lora-instruct - Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA
BELLE - BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型)
hyde - HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels
multi-lora-fine-tune - Provide Efficient LLM Fine-Tune via Multi-LoRA Optimization
ReAct - [ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
llama2-haystack - Using Llama2 with Haystack, the NLP/LLM framework.
gpt-j-fine-tuning-example - Fine-tuning 6-Billion GPT-J (& other models) with LoRA and 8-bit compression
alpaca-lora - Instruct-tune LLaMA on consumer hardware
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.