exllamav2
LocalAI
exllamav2 | LocalAI | |
---|---|---|
17 | 83 | |
3,010 | 20,346 | |
- | 10.5% | |
9.8 | 9.9 | |
3 days ago | 2 days ago | |
Python | C++ | |
MIT License | MIT License |
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.
exllamav2
- Running Llama3 Locally
-
Mixture-of-Depths: Dynamically allocating compute in transformers
There are already some implementations out there which attempt to accomplish this!
Here's an example: https://github.com/silphendio/sliced_llama
A gist pertaining to said example: https://gist.github.com/silphendio/535cd9c1821aa1290aa10d587...
Here's a discussion about integrating this capability with ExLlama: https://github.com/turboderp/exllamav2/pull/275
And same as above but for llama.cpp: https://github.com/ggerganov/llama.cpp/issues/4718#issuecomm...
-
What do you use to run your models?
Sorry, I'm somewhat familiar with this term (I've seen it as a model loader in Oobabooga), but still not following the correlation here. Are you saying I should instead be using this project in lieu of llama.cpp? Or are you saying that there is, perhaps, an exllamav2 "extension" or similar within llama.cpp that I can use?
-
I just started having problems with the colab again. I get errors and it just stops. Help?
EDIT: I reported the bug to the exllamav2 Github. It's actually already fixed, just not on any current built release.
-
Yi-34B-200K works on a single 3090 with 47K context/4bpw
install exllamav2 from git with pip install git+https://github.com/turboderp/exllamav2.git. Make sure you have flash attention 2 as well.
-
Tested: ExllamaV2's max context on 24gb with 70B low-bpw & speculative sampling performance
Recent releases for exllamav2 brings working fp8 cache support, which I've been very excited to test. This feature doubles the maximum context length you can run with your model, without any visible downsides.
-
Show HN: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context
Without batching, I was actually thinking that's kind of modest.
ExllamaV2 will get 48 tokens/s on a 4090, which is much slower/cheaper than an H100:
https://github.com/turboderp/exllamav2#performance
I didn't test codellama, but the 3090 TI figures are in the ballpark of my generation speed on a 3090.
-
Guide for Llama2 70b model merging and exllama2 quantization
First, you need the convert.py script from turboderp's Exllama2 repo. You can read all about the convert.py arguments here.
-
LLM Falcon 180B Needs 720GB RAM to Run
> brute aggressive quantization
Cutting edge quantization like ExLlama's EX2 is far from brute force: https://github.com/turboderp/exllamav2#exl2-quantization
> The format allows for mixing quantization levels within a model to achieve any average bitrate between 2 and 8 bits per weight. Moreover, it's possible to apply multiple quantization levels to each linear layer, producing something akin to sparse quantization wherein more important weights (columns) are quantized with more bits. The same remapping trick that lets ExLlama work efficiently with act-order models allows this mixing of formats to happen with little to no impact on performance. Parameter selection is done automatically by quantizing each matrix multiple times, measuring the quantization error (with respect to the chosen calibration data) for each of a number of possible settings, per layer. Finally, a combination is chosen that minimizes the maximum quantization error over the entire model while meeting a target average bitrate.
Llama.cpp is also working on a feature that let's a small model "guess" the output of a big model which then "checks" it for correctness. This is more of a performance feature, but you could also arrange it to accelerate a big model on a small GPU.
- 70B Llama 2 at 35tokens/second on 4090
LocalAI
- LocalAI: Self-hosted OpenAI alternative reaches 2.14.0
- Drop-In Replacement for ChatGPT API
- Voxos.ai – An Open-Source Desktop Voice Assistant
- Ask HN: Set Up Local LLM
- FLaNK Stack Weekly 11 Dec 2023
- Is there any open source app to load a model and expose API like OpenAI?
-
What do you use to run your models?
If you're running this as a server, I would recommend LocalAI https://github.com/mudler/LocalAI
-
OpenAI Switch Kit: Swap OpenAI with any open-source model
LocalAI can do that: https://github.com/mudler/LocalAI
https://localai.io/features/openai-functions/
-
"ChatGPT romanesc"
De inspirație, LocalAI, un replacement la OpenAI. E deja hot pe GitHub.
-
Local LLM's to run on old iMac / Hardware
Your hardware should be fine for inferencing, as long as you don't bother trying to get the GPU working.
My $0.02 would be to try getting LocalAI running on your machine with OpenCL/CLBlas acceleration for your CPU. If you're running other things, you could limit the inferencing process to 2 or 3 threads. That should get it working; I've been able to inference even 13b models on cheap Rockchip SOCs. Your CPU should be fine, even if it's a little outdated.
LocalAI: https://github.com/mudler/LocalAI
Some decent models to start with:
TinyLlama (extremely small/fast): https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.3-GGU...
Dolphin Mistral (larger size, better responses: https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF
What are some alternatives?
llama.cpp - LLM inference in C/C++
gpt4all - gpt4all: run open-source LLMs anywhere
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
SillyTavern - LLM Frontend for Power Users.
llama-cpp-python - Python bindings for llama.cpp
ChatGPT-AutoExpert - 🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
OmniQuant - [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
BlockMerge_Gradient - Merge Transformers language models by use of gradient parameters.
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.