llama
KoboldAI-Client
Our great sponsors
llama | KoboldAI-Client | |
---|---|---|
3 | 185 | |
35 | 3,344 | |
- | - | |
1.6 | 6.3 | |
about 1 year ago | about 2 months ago | |
Python | ||
GNU General Public License v3.0 only | 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
-
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
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).
-
Tips for using Kobold with Venus? I am pretty new at everything.
GPT-J 6B is a pretty weak and outdated model. Nerys 13B would probably give you better replies but they lean more towards SFW stuff. Erebus was their best model for erotic roleplay but they removed it as it went against Google's TOS. You can check out their documentation here.
-
I can't do this y'all
If you do have that kind of hardware, the next step would be looking for what model to run. I came across Kobold's models. Their main github page is here: https://github.com/KoboldAI/KoboldAI-Client
-
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?
-
How to get a KoboldAI URL API key!
Click this link. ---> https://github.com/KoboldAI/KoboldAI-Client/tree/main
-
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.
What are some alternatives?
llama.cpp - LLM inference in C/C++
TavernAI - Atmospheric adventure chat for AI language models (KoboldAI, NovelAI, Pygmalion, OpenAI chatgpt, gpt-4)
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
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
stanford_alpaca - Code and documentation to train Stanford's Alpaca models, and generate the data.
KoboldAI
tinygrad - You like pytorch? You like micrograd? You love tinygrad! ❤️ [Moved to: https://github.com/tinygrad/tinygrad]
Clover-Edition - State of the art AI plays dungeon master to your adventures.
llama - Inference code for Llama models
stable-diffusion-webui - Stable Diffusion web UI