Who needs GitHub Copilot when you can roll your own AI code assistant at home • The Register

[https://www.theregister.com/AMP/2024/08/18/self_hosted_github_copilot] - 2024-08-26 16:07:40 - public:mzimmerm

ai, code, good, home, ide, intellij, local, model, todo, train - 10 | id:1492807 -

Honey, I shrunk the LLM! A beginner's guide to quantization • The Register

[https://www.theregister.com/2024/07/14/quantization_llm_feature/?td=rt-9cs] - 2024-07-26 19:16:19 - public:mzimmerm

ai, good, model, quantize, todo - 5 | id:1492626 -

Perplexity

[https://www.perplexity.ai/] - 2024-07-23 19:36:39 - public:mzimmerm

ai, chat, good, search - 4 | id:1492596 -

Replacement of Google for search

The Best GPUs for Deep Learning in 2023 — An In-depth Analysis

[https://timdettmers.com/2023/01/30/which-gpu-for-deep-learning/] - 2024-03-22 02:50:52 - public:mzimmerm

ai, good, gpu, learn, llm, todo, train - 7 | id:1490076 -

BERT Transformers – How Do They Work? | Exxact Blog

[https://www.exxactcorp.com/blog/Deep-Learning/how-do-bert-transformers-work] - 2024-03-11 04:39:00 - public:mzimmerm

ai, bert, doc, good, llm, parameter, progress, todo, transformer - 9 | id:1489882 -

Excellent document about BERT transformers / models and their parameters: - L=number of layers. - H=size of the hidden layer = number of vectors for each word in the sentence. - A = Number of self-attention heads - Total parameters.

6 Ways to Run LLMs Locally (also how to use HuggingFace)

[https://semaphoreci.com/blog/local-llm] - 2024-03-05 21:45:35 - public:mzimmerm

ai, good, huggingface, llm, local - 5 | id:1489820 -

Various methods to run LLM models locally hugging face is only one of them.

deepseek-ai (DeepSeek)

[https://huggingface.co/deepseek-ai] - 2024-03-04 10:24:32 - public:mzimmerm

ai, best, code, deepseek, good, huggingface, instruct, llm, model, newspeak, small - 11 | id:1489786 -

They have the 1.3B version!!! This may be the best to start with Newspeak. Should work train even on huggingcface

deepseek-ai/deepseek-coder-6.7b-instruct · Hugging Face

[https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct] - 2024-03-04 10:13:20 - public:mzimmerm

ai, code, generate, good, llm, model, newspeak, opensource - 8 | id:1489783 -

Another possible model. For coding capabilities, Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.

StarCoder: A State-of-the-Art LLM for Code

[https://huggingface.co/blog/starcoder] - 2024-03-04 07:43:17 - public:mzimmerm

ai, code, generate, good, huggingface, llm, model, newspeak - 8 | id:1489773 -

Article has comparison with other code-LLM models

stabilityai (Stability AI) - Stable Diffusion running on Huggingface

[https://huggingface.co/stabilityai] - 2024-03-04 06:24:17 - public:mzimmerm

ai, chat, good, home, huggingface, image, instruct, model, newspeak, small, stabilityai, stablecode - 12 | id:1489767 -

Chat, models. Not open source, but instruct and relatively small (3B). The 3B instruct may be the best to try on Newspeak.

AI Code Tools: The Ultimate Guide in 2024

[https://codesubmit.io/blog/ai-code-tools/] - 2024-03-03 08:19:57 - public:mzimmerm

ai, code, generate, good, model, tool - 6 | id:1489745 -

AI Code tools : Good summary. Does not talk about which pre-trained model they use. One is gemini (bard) -> alphacode2

Introduction - Hugging Face NLP Course

[https://huggingface.co/learn/nlp-course/chapter1/1] - 2024-03-03 07:10:04 - public:mzimmerm

ai, course, good, nlp, todo, tutorial - 6 | id:1489742 -

Natural Languge processing - full course.

BERT 101 - State Of The Art NLP Model Explained

[https://huggingface.co/blog/bert-101] - 2024-03-03 06:50:18 - public:mzimmerm

ai, bert, best, good, model, progress, summary, transform - 8 | id:1489741 -

Best summary of Natural Language Processing and terms - model (a language model - e.g. BertModel, defines encoder and decoder and their properties), transformer (a specific neural network based on attention paper), encoder (series of transformers on input), decoders (series of transformers on output). Bert does NOT use decoder. TensorFlow and PyTorch are possible backends to Transformers (NN). Summary: BERT is a highly complex and advanced language model that helps people automate language understanding.

BERT vs GPT: A Tale of Two Transformers That Revolutionized NLP | by Tavva Prudhvith | Medium

[https://medium.com/@prudhvithtavva/bert-vs-gpt-a-tale-of-two-transformers-that-revolutionized-nlp-11fff8e61984] - 2024-03-03 06:41:37 - public:mzimmerm

ai, bert, good, gpt, model, transform - 6 | id:1489740 -

Fine-tune a pretrained model

[https://huggingface.co/docs/transformers/training] - 2024-03-02 10:39:40 - public:mzimmerm

ai, bert, code, example, good, huggingface, llm, notebook, progress, train, train-bert-on-yelp, tutorial - 12 | id:1489730 -

Use the Bert model to train on Yelp dataset

How to train a new language model from scratch using Transformers and Tokenizers

[https://huggingface.co/blog/how-to-train] - 2024-03-02 09:48:13 - public:mzimmerm

ai, best, doc, good, language, llm, model, todo, train - 9 | id:1489725 -

Describes how to train a new language (desperanto) model.

Generative AI in a Nutshell - how to survive and thrive in the age of AI - YouTube

[https://www.youtube.com/watch?v=2IK3DFHRFfw] - 2024-03-02 08:48:33 - public:mzimmerm

ai, basic, generative, good - 4 | id:1489722 -

rabbit — keynote

[https://www.rabbit.tech/keynote] - 2024-01-30 07:21:28 - public:mzimmerm

ai, computer, future, good, rabbit, software - 6 | id:1489435 -

Poe

[https://poe.com/] - 2024-01-03 18:18:31 - public:mzimmerm

ai, chatgpt, good, gpt, poe - 5 | id:1489014 -

Poe is a UI for ChatGpt

BigCode - Playground - a Hugging Face Space by bigcode

[https://huggingface.co/spaces/bigcode/bigcode-playground] - 2023-12-10 00:38:55 - public:mzimmerm

ai, bigcode, code, generate, good, model, newspeak, playground, software, starcoder - 10 | id:1485780 -

Look for models that could be used in Newspeak

yabs.io

Yet Another Bookmarks Service

Search

Results