Anima
33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU (by lyogavin)
multi-lora-fine-tune
Provide Efficient LLM Fine-Tune via Multi-LoRA Optimization (by TUDB-Labs)
| Anima | multi-lora-fine-tune | |
|---|---|---|
| 3 | 1 | |
| 2,881 | 182 | |
| - | 15.9% | |
| 9.1 | 9.3 | |
| 13 days ago | 7 days ago | |
| Jupyter Notebook | Python | |
| Apache License 2.0 | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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
Posts with mentions or reviews of Anima.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-12-27.
- 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.
multi-lora-fine-tune
Posts with mentions or reviews of multi-lora-fine-tune.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-12-06.
-
Has anyone tried out the ASPEN-Framework for LoRA Fine-Tuning yet and can share their experience?
I want to train a Code LLaMA on some data, and I am looking for a Framework or Technique to train this on my PC with a 3090 Ti in it. In my research, I stumbled across the paper "ASPEN: High-Throughput LoRA Fine-Tuning of Large Language Models with a Single GPU" https://arxiv.org/abs/2312.02515 with this GitHub project: https://github.com/TUDB-Labs/multi-lora-fine-tune.
What are some alternatives?
When comparing Anima and multi-lora-fine-tune you can also consider the following projects:
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.
unsloth - Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
FastLoRAChat - Instruct-tune LLaMA on consumer hardware with shareGPT data
Finetune_LLMs - Repo for fine-tuning Casual LLMs
fin-llama - LLAMA specialized on finance
BELLE - BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）