llama
Open-Assistant
Our great sponsors
llama | Open-Assistant | |
---|---|---|
3 | 329 | |
35 | 36,647 | |
- | 0.8% | |
1.6 | 8.3 | |
about 1 year ago | 4 days ago | |
Python | ||
GNU General Public License v3.0 only | 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.
llama
-
Alpaca- An Instruct Tuned Llama 7B. Responses on par with txt-DaVinci-3. Demo up
> All the magic of "7B LLaMA running on a potato" seems to involve lowering precision down to f16 and then further quantizing to int4.
LLaMa weights are f16s to start out with, no lowering necessary to get to there.
You can stream weights from RAM to the GPU pretty efficiently. If you have >= 32GB ram and >=2GB vram my code here should work for you: https://github.com/gmorenz/llama/tree/gpu_offload
There's probably a cleaner version of it somewhere else. Really you should only need >= 16 GB ram, but the (meta provided) code to load the initial weights is completely unnecessarily making two copies of the weights in RAM simultaneously.
-
LLaMA-7B in Pure C++ with full Apple Silicon support
My code for this is very much not high quality, but I have a CPU + GPU + SSD combination: https://github.com/gmorenz/llama/tree/ssd
Usage instructions in the commit message: https://github.com/facebookresearch/llama/commit/5be06e56056...
At least with my hardware this runs at "[size of model]/[speed of SSD reads]" tokens per second, which (up to some possible further memory reduction so you can run larger batches at once on the same GPU) is a good as it gets when you need to read the whole model from disk each token.
At a 125GB and a 2MB/s read (largest model, what I get from my ssd) that's 60 seconds per token (1 day per 1440 words), which isn't exactly practical. Which is really the issue here, if you need to stream the model from an SSD because you don't have enough RAM, it is just a fundamentally slow process.
You could probably optimize quite a bit for batch throughput if you're ok with the latency though.
-
Llama-CPU: Fork of Facebooks LLaMa model to run on CPU
I don't know about this fork specifically, but in general yes absolutely.
Even without enough ram, you can stream model weights from disk and run at [size of model/disk read speed] seconds per token.
I'm doing that on a small GPU with this code, but it should be easy to get this working with the CPU as compute instead (and at least with my disk/CPU, I'm not even sure that it would run even slower, I think disk read would probably still be the bottleneck)
https://github.com/gmorenz/llama/tree/ssd
Open-Assistant
-
Best open source AI chatbot alternative?
For open assistant, the code: https://github.com/LAION-AI/Open-Assistant/tree/main/inference
-
GPT-4 Turbo for free with no sign up, and most importantly no Bing
Is this being used to collect chat results for synthetic data and/or training like https://github.com/LAION-AI/Open-Assistant did? I believe they gave away GPT-4 api calls via a text interface and absorbed the cost to later build a dataset of chats.
-
OpenAI now sends email threats?!
https://open-assistant.io seems to have the same guardrails, as ChatGPT. Tried it on several prompts and it wouldn't comply.
- ChatGPT-Antworten nach Schulnoten bewerten
-
Chat GPT Alternatives?
Open-Assistant [https://open-assistant.io/]
-
What are the best AI tools you've ACTUALLY used?
Open Assistant by LAION AI on GitHub
-
Keep Artificial Intelligence Free, protect it from monopolies: please sign this petition
To add to this if you want something for free or at least close to free, contribute to OpenSource projects like https://open-assistant.io/
-
If I had to get someone from total zero to ChatGPT power user
Also, there are fairly useful alternatives like GPT4ALL and Open Assistant that you can run locally.
-
Compiling a Comprehensive List of Publicly Usable LLM Q&A Services - Need Your Input!
https://open-assistant.io - oasst-sft-6-llama-30b
- Proposal for a Crowd-Sourced AI Feedback System
What are some alternatives?
llama.cpp - LLM inference in C/C++
KoboldAI-Client
ChatGLM-6B - ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
llama-mps - Experimental fork of Facebooks LLaMa model which runs it with GPU acceleration on Apple Silicon M1/M2
stanford_alpaca - Code and documentation to train Stanford's Alpaca models, and generate the data.
llama - Inference code for Llama models
tinygrad - You like pytorch? You like micrograd? You love tinygrad! ❤️ [Moved to: https://github.com/tinygrad/tinygrad]
gpt4all - gpt4all: run open-source LLMs anywhere