blog
WizardLM
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.
blog
-
Refact LLM: New 1.6B code model reaches 32% HumanEval and is SOTA for the size
[4] https://github.com/huggingface/blog/blob/main/starcoder.md
-
A comprehensive guide to running Llama 2 locally
If you just want to do inference/mess around with the model and have a 16GB GPU, then this[0] is enough to paste into a notebook. You need to have access to the HF models though.
0. https://github.com/huggingface/blog/blob/main/llama2.md#usin...
-
Let’s train your first Offline Decision Transformer model from scratch 🤖
The hands-on 👉https://github.com/huggingface/blog/blob/main/notebooks/101_train-decision-transformers.ipynb
-
How to switch to half precision fp16?
I'm also running the optimized script but it doesn't run with 512x512 on my RTX3050 Ti mobile. On this website, they recommend to switch to fp16 for GPUs with less than 10gb of vram.
-
Are people hiding their deep learning code?
Here's a notebook illustrating how to train a language model from scratch: https://github.com/huggingface/blog/blob/master/notebooks/01_how_to_train.ipynb
WizardLM
- FLaNK AI-April 22, 2024
-
Refact LLM: New 1.6B code model reaches 32% HumanEval and is SOTA for the size
This is interesting work, and a good contribution, but there is no need to mislead people.
[1] https://github.com/nlpxucan/WizardLM
-
Continue with LocalAI: An alternative to GitHub's Copilot that runs everything locally
If you pair this with the latest WizardCoder models, which have a fairly better performance than the standard Salesforce Codegen2 and Codegen2.5, you have a pretty solid alternative to GitHub Copilot that runs completely locally.
- WizardCoder context?
- The world's most-powerful AI model suddenly got 'lazier' and 'dumber.' A radical redesign of OpenAI's GPT-4 could be behind the decline in performance.
-
Official WizardLM-13B-V1.1 Released! Train with Only 1K Data! Can Achieve 86.32% on AlpacaEval!
(We will update the demo links in our github.)
-
GPT-4 API general availability
In terms of speed, we're talking about 140t/s for 7B models, and 40t/s for 33B models on a 3090/4090 now.[1] (1 token ~= 0.75 word) It's quite zippy. llama.cpp performs close on Nvidia GPUs now (but they don't have a handy chart) and you can get decent performance on 13B models on M1/M2 Macs.
You can take a look at a list of evals here: https://llm-tracker.info/books/evals/page/list-of-evals - for general usage, I think home-rolled evals like llm-jeopardy [2] and local-llm-comparison [3] by hobbyists are more useful than most of the benchmark rankings.
That being said, personally I mostly use GPT-4 for code assistance to that's what I'm most interested in, and the latest code assistants are scoring quite well: https://github.com/abacaj/code-eval - a recent replit-3b fine tune the human-eval results for open models (as a point of reference, GPT-3.5 gets 60.4 on pass@1 and 68.9 on pass@10 [4]) - I've only just started playing around with it since replit model tooling is not as good as llamas (doc here: https://llm-tracker.info/books/howto-guides/page/replit-mode...).
I'm interested in potentially applying reflexion or some of the other techniques that have been tried to even further increase coding abilities. (InterCode in particular has caught my eye https://intercode-benchmark.github.io/)
[1] https://github.com/turboderp/exllama#results-so-far
[2] https://github.com/aigoopy/llm-jeopardy
[3] https://github.com/Troyanovsky/Local-LLM-comparison/tree/mai...
[4] https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder
-
WizardLM-13B-V1.0-Uncensored
You talking about this? https://github.com/nlpxucan/WizardLM
-
What 7b llm to use
The smallest model that is close to competent at code is WizardCoder 15B.. https://github.com/nlpxucan/WizardLM/
-
16-Jun-2023
WizardCoder: Empowering Code Large Language Models with Evol-Instruct (https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder)
What are some alternatives?
text-generation-inference - Large Language Model Text Generation Inference
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
llm-humaneval-benchmarks
awesome-notebooks - A powerful data & AI notebook templates catalog: prompts, plugins, models, workflow automation, analytics, code snippets - following the IMO framework to be searchable and reusable in any context.
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
QuantumKatas - Tutorials and programming exercises for learning Q# and quantum computing
airoboros - Customizable implementation of the self-instruct paper.
stable-diffusion - Optimized Stable Diffusion modified to run on lower GPU VRAM
promptfoo - Test your prompts, models, and RAGs. Catch regressions and improve prompt quality. LLM evals for OpenAI, Azure, Anthropic, Gemini, Mistral, Llama, Bedrock, Ollama, and other local & private models with CI/CD integration.
Practical_RL - A course in reinforcement learning in the wild
can-ai-code - Self-evaluating interview for AI coders