OmniQuant
llamafile
OmniQuant | llamafile | |
---|---|---|
4 | 38 | |
592 | 15,628 | |
11.3% | 31.4% | |
7.7 | 9.6 | |
2 months ago | 6 days ago | |
Python | C++ | |
MIT License | GNU General Public License v3.0 or later |
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.
OmniQuant
-
Run Mistral 7B on M1 Mac
Not on iOS. On macOS, I personally think WizardLM 13B v1.2 is a very strong model and keep hearing good things about it from users on our discord and in support emails. Now that there's OmniQuant support for Mixtral models[1], I'm plan to add support for Mixtral-8x7B-Instruct-v0.1 in the next version of the macOS app, which in my tests, looks like a very good all purpose model that's also pretty good at coding. It's pretty memory hungry (~41GB of RAM), but that's the price to pay for an uncompromising implementation. Existing quantized implementations quantize the MoE gates, leading to a significant drop in perplexity when compared with results from fp16 inference.
[1]: https://github.com/OpenGVLab/OmniQuant/commit/798467
- OmniQuant of Falcon-180B has been released!
-
70B Llama 2 at 35tokens/second on 4090
I think OmniQuant is notable because it shifts the bend of the curve to 3-bit. While < 3-bit still ramps up, it's notable in that it's usable and doesn't go asymptotic: https://github.com/OpenGVLab/OmniQuant/blob/main/imgs/weight...
What EXL2 seems to bring to the table is that you can target an arbitrary quantize bit-weight (eg, if you're a bit short on VRAM, you don't need to go from 4->3 or 3->2, but can specify say 3.75bwp). You have some control w/ other schemes by setting group size, or with k-quants, but EXL2 is definitely allows you to be finer grained. I haven't gotten a chance to sit down with EXL2 yet, but if no one else does it, it's on my todo-list to be able to do 1:1 perplexity and standard benchmark evals on all the various new quantization methods, just as a matter of curiosity.
- OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
llamafile
- FLaNK-AIM Weekly 06 May 2024
- llamafile v0.8
-
Mistral AI Launches New 8x22B Moe Model
I think the llamafile[0] system works the best. Binary works on the command line or launches a mini webserver. Llamafile offers builds of Mixtral-8x7B-Instruct, so presumably they may package this one up as well (potentially a quantized format).
You would have to confirm with someone deeper in the ecosystem, but I think you should be able to run this new model as is against a llamafile?
[0] https://github.com/Mozilla-Ocho/llamafile
-
Apple Explores Home Robotics as Potential 'Next Big Thing'
Thermostats: https://www.sinopetech.com/en/products/thermostat/
I haven't tried running a local text-to-speech engine backed by an LLM to control Home Assistant. Maybe someone is working on this already?
TTS: https://github.com/SYSTRAN/faster-whisper
LLM: https://github.com/Mozilla-Ocho/llamafile/releases
LLM: https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-D...
It would take some tweaking to get the voice commands working correctly.
-
LLaMA Now Goes Faster on CPUs
While I did not succeed in making the matmul code from https://github.com/Mozilla-Ocho/llamafile/blob/main/llamafil... work in isolation, I compared eigen, openblas, and mkl: https://gist.github.com/Dobiasd/e664c681c4a7933ef5d2df7caa87...
In this (very primitive!) benchmark, MKL was a bit better than eigen (~10%) on my machine (i5-6600).
Since the article https://justine.lol/matmul/ compared the new kernels with MLK, we can (by transitivity) compare the new kernels with Eigen this way, at least very roughly for this one use-case.
-
Llamafile 0.7 Brings AVX-512 Support: 10x Faster Prompt Eval Times for AMD Zen 4
Yes, they're just ZIP files that also happen to be actually portable executables.
https://github.com/Mozilla-Ocho/llamafile?tab=readme-ov-file...
-
Show HN: I made an app to use local AI as daily driver
have you seen llamafile[0]?
[0] https://github.com/Mozilla-Ocho/llamafile
- FLaNK Stack 26 February 2024
-
Gemma.cpp: lightweight, standalone C++ inference engine for Gemma models
llama.cpp has integrated gemma support. So you can use llamafile for this. It is a standalone executable that is portable across most popular OSes.
https://github.com/Mozilla-Ocho/llamafile/releases
So, download the executable from the releases page under assets. You want either just main or just server. Don't get the huge ones with the model inlined in the file. The executable is about 30MB in size,
https://github.com/Mozilla-Ocho/llamafile/releases/download/...
-
Ollama releases OpenAI API compatibility
The improvements in ease of use for locally hosting LLMs over the last few months have been amazing. I was ranting about how easy https://github.com/Mozilla-Ocho/llamafile is just a few hours ago [1]. Now I'm torn as to which one to use :)
1: Quite literally hours ago: https://euri.ca/blog/2024-llm-self-hosting-is-easy-now/
What are some alternatives?
gptq - Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
exllamav2 - A fast inference library for running LLMs locally on modern consumer-class GPUs
ollama-webui - ChatGPT-Style WebUI for LLMs (Formerly Ollama WebUI) [Moved to: https://github.com/open-webui/open-webui]
Cgml - GPU-targeted vendor-agnostic AI library for Windows, and Mistral model implementation.
langchain - 🦜🔗 Build context-aware reasoning applications
LLaVA - [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
llama.cpp - LLM inference in C/C++
safetensors - Simple, safe way to store and distribute tensors
LocalAIVoiceChat - Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.
chatgpt-web - ChatGPT web interface using the OpenAI API
TinyLlama - The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.