llama.cpp
basaran
Our great sponsors
llama.cpp | basaran | |
---|---|---|
765 | 22 | |
55,117 | 1,281 | |
- | - | |
9.9 | 10.0 | |
5 days ago | 3 months ago | |
C++ | Python | |
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.
llama.cpp
-
Embeddings are a good starting point for the AI curious app developer
Have just done this recently for local chat with pdf feature in https://recurse.chat. (It's a macOS app that has built-in llama.cpp server and local vector database)
Running an embedding server locally is pretty straightforward:
- Get llama.cpp release binary: https://github.com/ggerganov/llama.cpp/releases
-
Mixtral 8x22B
Most inference servers are OpenAI-compatibile. Even the "official" llama-cpp server should work fine: https://github.com/ggerganov/llama.cpp/blob/master/examples/...
-
Ollama 0.1.32: WizardLM 2, Mixtral 8x22B, macOS CPU/GPU model split
Ah, thanks for this! I can't edit my parent comment that you replied to any longer unfortunately.
As I said, I only compared the contributors graphs [0] and checked for overlaps. But those apparently only go back about year and only list at most 100 contributors ranked by number of commits.
[0]: https://github.com/ollama/ollama/graphs/contributors and https://github.com/ggerganov/llama.cpp/graphs/contributors
Quite possible that llama.cpp already supports WizardLM 2: https://github.com/ggerganov/llama.cpp/issues/6691
This doesn’t seem correct to me. I saw in another pull request, an Ollama contributor said:
> As you pointed out, we carry patches, although in general we try to upstream those.
— https://github.com/ollama/ollama/issues/2534#issuecomment-19...
So I followed the link to his profile and saw that he has opened some non-documentation pull requests for llama.cpp:
https://github.com/ggerganov/llama.cpp/pull/5244
https://github.com/ggerganov/llama.cpp/pull/5576
I didn’t dig any deeper, but it took me less than thirty seconds to find those so I expect there are more.
-
KodiBot - Local Chatbot App for Desktop
KodiBot is a desktop app that enables users to run their own AI chat assistants locally and offline on Windows, Mac, and Linux operating systems. KodiBot is a standalone app and does not require an internet connection or additional dependencies to run local chat assistants. It supports both Llama.cpp compatible models and OpenAI API.
-
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...
-
The lifecycle of a code AI completion
For those who might not be aware of this, there is also an open source project on GitHub called "Twinny" which is an offline Visual Studio Code plugin equivalent to Copilot: https://github.com/rjmacarthy/twinny
It can be used with a number of local model services. Currently for my setup on a NVIDIA 4090, I'm running both the base and instruct model for deepseek-coder 6.7b using 5_K_M Quantization GGUF files (for performance) through llama.cpp "server" where the base model is for completions and the instruct model for chat interactions.
llama.cpp: https://github.com/ggerganov/llama.cpp/
deepseek-coder 6.7b base GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GGU...
deepseek-coder 6.7b instruct GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct...
-
More Agents Is All You Need: LLMs performance scales with the number of agents
If I'm reading this correctly, they had to discard Llama 2 answers and only use GPT-3.5 given answers to test the hypothesis.
GPT-3.5 answering questions through the OAI API alone is not an acceptable method of testing problem solving ability across a range of temperatures. OpenAI does some blackbox wizardry on their end.
There are many complex and clever sampling techniques for which temperature is just one (possibly dynamic) component
One example from the llama.cpp codebase is dynamic temperature sampling
https://github.com/ggerganov/llama.cpp/pull/4972/files
Not sure what you mean by whole model state given that there are tens of thousands of possible tokens and the models have billions of parameters in XX,XXX-dimensional space. How many queries across how many sampling methods might you need? Err..how much time? :)
basaran
- OpenLLM
-
Langchain and self hosted LLaMA hosted API
What are the current best "no reinventing the wheel" approaches to have Langchain use an LLM through a locally hosted REST API, the likes of Oobabooga or hyperonym/basaran with streaming support for 4-bit GPTQ?
-
Run and create custom ChatGPT-like bots with OpenChat
Disclaimer: I am curating LLM-tools on github [1]
A few thoughts:
* allow for custom endpoint URLs, this way people can use open source LLMs with a fake openAI API backend like basaran[2] or llama-api-server[3]
* look into better embedding methods for info-retrieval like InstructorEmbeddings or Document Summary Index
* Don't use a single embedding per content item, use multiple to increase retrieval quality
1 https://github.com/underlines/awesome-marketing-datascience/...
-
1-Jun-2023
open-source alternative to the OpenAI text completion API (https://github.com/hyperonym/basaran)
- Introducing Basaran: self-hosted open-source alternative to the OpenAI text completion API
-
Ask HN: What's the best self hosted/local alternative to GPT-4?
Guanaco-65B[0] using Basaran[1] for your OpenAI compatible API. You can use any ChatGPT front-end which lets you change the OpenAI endpoint URL.
[0] An fp4 finetune of LLaMA-30B by Tim Dettmers
-
Are all the finetunes stupid?
For lm-eval, I think you'd either need to take GPTQ's inference script and shim it into a model: https://github.com/EleutherAI/lm-evaluation-harness/tree/master/lm_eval/models or you might be able to use a project like https://github.com/hyperonym/basaran and then you could use the gpt3 model...
-
Using the API in Node
There are also: - Basaran repo: "Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models". "...Compatibility with OpenAI API and client libraries..."; - llama-cpp-python repo: "Simple Python bindings for @ggerganov's llama.cpp library...". "...OpenAI-like API...".
-
Researcher looking for help with how to prepare a finetuning dataset for models like Bloomz and Cerebras-GPT
I want to start with a totally freely available model, so again, that excludes things like LLaMA where the weights are only available through a wait list. The two models that most get my attention and (I think, and hope) fit my criteria of open availability are Cerebras-GPT (13b) and Bloomz (7b). The tools to process and fine-tune that seem most feasible to me, from my limit knowledge, are xturing and basaran.
-
ChatGLM, an open-source, self-hosted dialogue language model and alternative to ChatGPT created by Tsinghua University, can be run with as little as 6GB of GPU memory.
It is served using Basaran, which also supports other text generation models available on Hugging Face hub. GitHub: https://github.com/hyperonym/basaran
What are some alternatives?
ollama - Get up and running with Llama 2, Mistral, Gemma, and other large language models.
gpt4all - gpt4all: run open-source LLMs anywhere
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
ggml - Tensor library for machine learning
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
rust-gpu - 🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
ChatGLM-6B - ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
safetensors - Simple, safe way to store and distribute tensors
AutoGPT - AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
alpaca-lora - Instruct-tune LLaMA on consumer hardware