dspy
unsloth
dspy | unsloth | |
---|---|---|
22 | 15 | |
10,820 | 8,282 | |
17.5% | 38.0% | |
9.9 | 9.4 | |
7 days ago | 9 days ago | |
Python | Python | |
MIT License | 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.
dspy
-
Computer Vision Meetup: Develop a Legal Search Application from Scratch using Milvus and DSPy!
Legal practitioners often need to find specific cases and clauses across thousands of dense documents. While traditional keyword-based search techniques are useful, they fail to fully capture semantic content of queries and case files. Vector search engines and large language models provide an intriguing alternative. In this talk, I will show you how to build a legal search application using the DSPy framework and the Milvus vector search engine.
-
Pydantic Logfire
I’ve observed that Pydantic - which we’ve used for years in our API stack - has become very popular in LLM applications, for its type-adjacent features. It serves as a foundational technology for prompting libraries like [DSPy](https://github.com/stanfordnlp/dspy) which are abstracting “up the stack” of LLM apps. (some opinions there)
Operating AI apps reveals a big challenge, in that debugging probabilistic code paths requires more than the usual introspective abilities, and in an environment where function calls can have very real monetary impact we have to be able to see what’s happening in the runtime. See LangChain’s hosted solution (can’t recall the name) that allows an operator to see prompts and responses “on the wire”. (It just occurred to me that Langchain and Pydantic have a lot in common here, in approach.)
Having a coupling between Pydantic - which is *just about* the data layer itself - and an observability tool seems very interesting to me, and having this come from the folks who built it does not seem unreasonable. WRT open source and monetization, I would be lying if I said I wasn’t a little worried - given the recent few months - but I am choosing to see this in a positive light, given this team’s “believability weight” (to overuse Dalio) and history of delivering solid and really useful tooling.
- Ask HN: Most efficient way to fine-tune an LLM in 2024?
-
Princeton group open sources "SWE-agent", with 12.3% fix rate for GitHub issues
DSPy is the best tool for optimizing prompts [0]: https://github.com/stanfordnlp/dspy
Think of it as a meta-prompt optimizer, it uses a LLM to optimize your prompts, to optimize your LLM.
-
Winner of the SF Mistral AI Hackathon: Automated Test Driven Prompting
Isn’t this just a very naive implementation of what DsPY does?
https://github.com/stanfordnlp/dspy
I don’t understand what is exceptional here.
-
Show HN: Fructose, LLM calls as strongly typed functions
Have you done any comparison with DSPy ? (https://github.com/stanfordnlp/dspy)
Feels very similiar to DSPy except you dont have optimizations yet. But I like your API and the programming model your are enforcing through this.
-
AI Prompt Engineering Is Dead
I'm interested in hearing if anyone has used DSPy (https://github.com/stanfordnlp/dspy) just for prompt optimization for GPT-3.5 or GPT-4. Was it worth the effort and much better than manual prompt iteration? Was the optimized prompt some weird incantation? Any other insights?
-
Ask HN: Are you using a GPT to prompt-engineer another GPT?
You should check out x.com/lateinteraction's DSPy — which is like an optimizer for prompts — https://github.com/stanfordnlp/dspy
- SuperDuperDB - how to use it to talk to your documents locally using llama 7B or Mistral 7B?
- FLaNK Stack Weekly for 12 September 2023
unsloth
-
Ask HN: Most efficient way to fine-tune an LLM in 2024?
Gemma 7b is 2.4x faster than HF + FA2.
Check out https://github.com/unslothai/unsloth for full benchmarks!
-
Gemma doesn't suck anymore – 8 bug fixes
Here are the missing links:
* Gemma, a family of open models from Google: https://ai.google.dev/gemma
* Unsloth is a tool/method for training models faster (IIUC): https://github.com/unslothai/unsloth
-
AMD ROCm Software Blogs
Thanks! Again, partnerships over customers. If you're experienced and have the technical chops to make a MI300x sing, we want to work with you. Our model is that we are the capex/opex investor for businesses. As much as I love software, Hot Aisle is more of a hardware business. Running super high end large scale compute is an extreme challenge in itself. We are less interested in building the software side of things and want to foster those who can focus on that side.
https://github.com/unslothai/unsloth/issues/160
https://github.com/search?q=repo%3Apredibase%2Florax+rocm&ty...
https://github.com/sgl-project/sglang/issues/157
https://github.com/casper-hansen/AutoAWQ (supports rocm)
-
Show HN: We got fine-tuning Mistral-7B to not suck
Unsloth’s colab notebooks for fine-tuning Mistral-7B are super easy to use and run fine in just about any colab instance:
https://github.com/unslothai/unsloth
It’s my default now for experimenting and basic training. If I want to get into the weeds with the training, I use axolotl, but 9/10, it’s not really necessary.
-
Mistral 7B Fine-Tune Optimized
If anyone wants to finetune their own Mistral 7b model 2.2x faster and use 62% less memory - give our open source package Unsloth a try! https://github.com/unslothai/unsloth a try! :)
-
Has anyone tried out the ASPEN-Framework for LoRA Fine-Tuning yet and can share their experience?
https://github.com/unslothai/unsloth seems good and more relevant to your aims perhaps but I haven't tried it.
-
Can we discuss MLOps, Deployment, Optimizations, and Speed?
The unsloth project offers some low-level optimizations for Llama et al, and as of today some prelim Mistral work (which I heard is the llama architecture?)
- Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning
-
80% faster, 50% less memory, 0% accuracy loss Llama finetuning
This seems to just be a link to the Unsloth Github repo[0], which in turn is the free version of Unsloth Pro/Max[1]. Maybe the link should be changed?
[0]: https://github.com/unslothai/unsloth
- 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning
What are some alternatives?
semantic-kernel - Integrate cutting-edge LLM technology quickly and easily into your apps
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
open-interpreter - A natural language interface for computers
llama.cpp - LLM inference in C/C++
playground - Play with neural networks!
nanoChatGPT - nanogpt turned into a chat model
MLflow - Open source platform for the machine learning lifecycle
gpt-fast - Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
FastMJPG - FastMJPG is a command line tool for capturing, sending, receiving, rendering, piping, and recording MJPG video with extremely low latency. It is optimized for running on constrained hardware and battery powered devices.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
prompt-engine-py - A utility library for creating and maintaining prompts for Large Language Models
accelerate - 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support