one-click-installers
WizardLM
| one-click-installers | WizardLM | |
|---|---|---|
| 18 | 38 | |
| 470 | 7,531 | |
| - | - | |
| 8.9 | 9.4 | |
| 8 months ago | 8 months ago | |
| Python | Python | |
| 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.
one-click-installers
-
amd gpus on windows support?
AMD does not offer installation options for ROCm on Windows. I'm not familiar with the workarounds to make it work; if you find a solution, you can contribute it to https://github.com/oobabooga/one-click-installers/
-
Oobabooga for Windows
Running start_windows.bat should take care of everything.
-
Quant-Cude Error?
Had the same issue, turns out I was using an old 1 click installer / updater, you need to use https://github.com/oobabooga/one-click-installers and reinstall everything from scratch
-
Cant find the "start: file.
Are you sure you're looking at the right folder? start_windows.bat is there. It's listed in the source code: https://github.com/oobabooga/one-click-installers
- Any UI that allows Windows + AMD GPU ?
- WizardLM-30B-Uncensored
-
13b-4bit-128g - Trying to run compressed model without success. ( problem exist only with 13b models for some reason ) No error code has been displayed.
one-click-installers/INSTRUCTIONS.TXT
-
GPT4All: A little helper to get started
https://github.com/oobabooga/one-click-installers/issues/56 they explain it over here.
-
Visual Studio compile errors
I solved this by adding the Individual components 2019 Windows 10 SDK, C++ CMake tools for Windows, and MSVC v142 - VS 2019 C++ build tools. See https://github.com/oobabooga/one-click-installers/issues/56
-
python setup.py bdist_wheel did not run successfully.
It appears one of the extensions isn't pre-compiled on install. I believe you have the same problem as listed here. https://github.com/oobabooga/one-click-installers/issues/56
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?
GPTQ-for-LLaMa - 4 bits quantization of LLaMa using GPTQ
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
gpt4all - gpt4all: run open-source LLMs anywhere
llm-humaneval-benchmarks
gradio - Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
KoboldAI
airoboros - Customizable implementation of the self-instruct paper.
WizardVicunaLM - LLM that combines the principles of wizardLM and vicunaLM
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.
micromamba-releases - Micromamba executables mirrored from conda-forge as Github releases
can-ai-code - Self-evaluating interview for AI coders