llama
KoboldAI-Client
Our great sponsors
llama | KoboldAI-Client | |
---|---|---|
180 | 185 | |
51,530 | 3,295 | |
5.2% | - | |
8.2 | 6.3 | |
6 days ago | 16 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | GNU Affero General Public License v3.0 |
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
-
DBRX: A New Open LLM
Ironically, the LLaMA license text [1] this is lifted verbatim from is itself copyrighted [2] and doesn't grant you the permission to copy it or make changes like s/meta/dbrx/g lol.
[1] https://github.com/meta-llama/llama/blob/main/LICENSE#L65
-
Markov Chains Are the Original Language Models
Predicting subsequent text is pretty much exactly what they do. Lots of very cool engineering that’s a real feat, but at its core it’s argmax(P(token|token,corpus)):
https://github.com/facebookresearch/llama/blob/main/llama/ge...
The engineering feats are up there with anything, but it’s a next token predictor.
- Meta AI releases Code Llama 70B
-
Stuff we figured out about AI in 2023
> Instead, it turns out a few hundred lines of Python is genuinely enough to train a basic version!
actually its not just a basic version. Llama 1/2's model.py is 500 lines: https://github.com/facebookresearch/llama/blob/main/llama/mo...
Mistral (is rumored to have) forked llama and is 369 lines: https://github.com/mistralai/mistral-src/blob/main/mistral/m...
and both of these are SOTA open source models.
-
[D] What is a good way to maintain code readability and code quality while scaling up complexity in libraries like Hugging Face?
In transformers, they tried really hard to have a single function or method to deal with both self and cross attention mechanisms, masking, positional and relative encodings, interpolation etc. While it allows a user to use the same function/method for any model, it has led to severe parameter bloat. Just compare the original implementation of llama by FAIR with the implementation by HF to get an idea.
-
Set up your own LMQL environment.
(myvenv) root@a176328806c7:/home# apt-get install git (myvenv) root@a176328806c7:/home# apt-get install wget (myvenv) root@a176328806c7:/home# git clone https://github.com/facebookresearch/llama.git (myvenv) root@a176328806c7:/home# cd llama/ (myvenv) root@a176328806c7:/home/llama# pip install -e . (myvenv) root@a176328806c7:/home/llama# ./download.sh
-
Ask HN: Why the LLaMA code base is so short
I was getting into LLM and I pick up some projects. I tried to dive into the code to see what is secret sauce.
But the code is so short to the point there is nothing to really read.
https://github.com/facebookresearch/llama
I then proceed to check https://github.com/mistralai/mistral-src and suprsingly it's same.
What is exactly those codebases? It feels like just download the models.
-
ExecuTorch: Enabling On-Device interference for embedded devices
Is it possible to execute a light weight language model, perhaps this https://github.com/facebookresearch/llama using ExecuTorch to run on smartphone in real time for a chatbot app ? Please share some guidance.
-
Our Team's Favourite Open Source Projects Right Now
Website: https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/ Github: https://github.com/facebookresearch/llama
- FLaNK Stack Weekly 5 September 2023
KoboldAI-Client
- No idea what I'm doing help
-
ChatGPT users drop for the first time as people turn to uncensored chatbots
You can use KoboldAI to run a LLM locally. There are hundreds / thousands of models on hugging face. Some uncensored ones are Pygmalion AI (chatbot), Erebus (story writing AI), or Vicuna (general purpose).
-
Question regarding model compatibility for Alpaca Turbo
Then there are graphical user interfaces like text-generation-webui and gpt4all for general purpose chat. There are also KoboldAI and SillyTavern, they have focus more on storytelling and roleplay and have tools to improve that.
-
Running Multiple AI Models Sequentially for a Conversation on a Single GPU
And finally the folks from the KoboldAi do some interesting stuff with Pseudocode and Soft-Prompts that might also be relevant.
- Summoning Life-Size Characters to Your Room: New Update for my Mixed Reality App!
- Feels like the censorship has gotten tighter recently, just me?
-
Difficulties installing Pygmalion 13b
Do you believe the problem could be that my KoboldAI is outdated? I did download the one from henk717 at https://github.com/KoboldAI/KoboldAI-Client but it was a little while ago.
-
Training code and dataset for ProfitsBot_V0 experiments
I'm not to familiar with kobald, but it looks like you would have to write an inputModifier and outputModifier, https://github.com/KoboldAI/KoboldAI-Client/pull/4
-
ADOBE being ADOBE...
This is a crowdsourced distributed cluster of Image generation workers and text generation workers.
-
How to run pygmalion: usefull links
The main branch of kai (https://github.com/KoboldAI/KoboldAI-Client) doesn't yet have the support for 4 bit models. That's a problem for people who have under 16gb of VRAM. I use a branch with 4 bit support: https://github.com/0cc4m/KoboldAI. Instructions are available there but basically you'll need to get both the original model https://huggingface.co/PygmalionAI/pygmalion-6b and the 4 bit version https://huggingface.co/mayaeary/pygmalion-6b-4bit-128g. Throw 4 bit safetensors file into the full model and rename it to "4bit-128g.safetensors".
What are some alternatives?
TavernAI - Atmospheric adventure chat for AI language models (KoboldAI, NovelAI, Pygmalion, OpenAI chatgpt, gpt-4)
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
KoboldAI
Clover-Edition - State of the art AI plays dungeon master to your adventures.
chatgpt-vscode - A VSCode extension that allows you to use ChatGPT
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
stable-diffusion-webui - Stable Diffusion web UI
ollama - Get up and running with Llama 2, Mistral, Gemma, and other large language models.