güzel bir ide'ye denk geldim demin: zerve ai

llm ve datasetleri sürükle bırak yaparak kolayca fine-tune edebiliyorsunuz.

huggingface ve bedrock entegrasyonu da varmış. yani modelleri oradan çekebilir veya host edebiliyormuşsunuz.

Python kullanarak derinlik tahmini yapabilirsiniz. Kodları görsellerde paylaştım.

Ben burada DPT-Large modelini kullandım. Daha farklı modellere Hugging Face’den bakabilirsiniz.

It finally happened! I made it to the Top 10 of the Open LLM Leaderboard by Hugging Face , right on the edge! Thank you all! ❤️

This is the very first fine-tuned model I've created based on Llama-3-70B, released by AI at Meta. I will be releasing 16 more fine-tuned models!🚀

最近、gpt2という言葉を見たんですよ。どこかというと、FineWebです。おそらくgpt2-chatbotはFineWebの副産物。作ったのはHugging Faceです。
huggingface.co/datasets/Huggi…

💫 Computer Vision Community Course now LIVE!

From the awesome Hugging Face🤗 folks + many amazing people from the computer vision community, comes the greatest computer vision course in the entire galaxy 🌌

This course banner was designed by the fantastic Isabella Bicalho-Frazeto

大規模学習は罠が多すぎる…

> 原因は、Huggingface Acceleratorの.prepare()メソッドにdataloaderを通していたからでした。...データセットの一部分を見ただけですべてのデータセットを見終わったとみなし、2epoch目に突入するという動作をしていることが明らかになりました
zenn.dev/tokyotech_lm/a…

为方便快捷下载到开源模型，在国内做了个Hugging Face模型镜像加速网站-AI快站。

aifasthub.com

AI快站的特点：
高速下载：提供的模型下载速度相对较快，减少等待时间
模型资源丰富：涵盖大部分常用开源模型，更新速度快
支持断点续传：提供下载器，大模型下载时遇到中断也不再是问题

llama-3-vision-alpha now works using Hugging Face transformers

The top AI talent is concentrated at these 9 companies per SignalFire

- OpenAI
- Anthropic
- MosaicML (now part of DataBricks)
- Cohere
- AI21 Labs
- Hugging Face
- Stability AI
- Midjourney
- Inflection (now part of Microsoft)

A full demo of DanTagGen + Kohaku XL is now available on HuggingFace Space!

'This Cute Dragon Girl Doesn't Exist'
huggingface.co/spaces/KBlueLe…

🎉 Our Llama3-8B-Chinese-Chat ranks 14th in overall trending on Huggingface, 2nd among Llama3 derivative models, and 1st among Llama3 Chinese derivative models! Thanks for your support!

🌟 I summarized our updates today in Fig. 3. See the details in the comments below:

llama3-8Bを日本語でファインチューニングしたものをhuggingfaceにアップしました。
10B以下のモデルでは日本語ベンチマークで最強です。llama3すごいですね。
LM Studioですぐに試せます。

以前の投稿でも書きましたが、ベンチマークが意味をなさなくなりつつあります
huggingface.co/lightblue/suzu…

Mixtral-8x22B-Instruct-v0.1を使って作ったAlpacaデータセット、HuggingFaceに置きました。
とりあえず実験的に作ったものなので1000データほどです。より綺麗で多いものに変えていくつもりです。
huggingface.co/datasets/Hachi…

Internistai 7b: Medical Language Model

Today we release the best 7b medical model, outperforming GPT-3.5 and achieving the first pass score on the USMLE! Our approach allows the model to retain the same general capabilities as the base model.

huggingface.co/internistai/ba…

🔥🔥 قدمت Hugging Face نموذج Open Medical-LLM، وهو معيار جديد لتقييم نماذج الذكاء الاصطناعي في مهام الرعاية الصحية.

Run IDM-VTON Locally

IDM-VTON lets you virtually try on any clothes with your own photo using AI. It works very well.

Wrote a 1-click launcher for the IDM-VTON Huggingface space gradio app. Works on all OS (Mac, Windows, Linux) Enjoy.

10M instructions could have been used to finetune LLaMa-3 instruct

So here are ~2.2M (>1B tokens) high quality instructions curated from ~30 popular datasets (~6B tokens) across various tasks including function-calling

8.8M to go 🚀

huggingface.co/datasets/0-her…

huggingface gg olunca elektriğin gelmesini bekler gibi bekliyoz

I am Qishen Ha, a Kaggle GrandMaster. I have just open-sourced a Llama3 model finetuned with Japanese dataset. Pls test it!

Kaggle GrandMaster の Qishen Ha です。日本語でFTされた Llama3 をオープンソースしました。テストお願いします！

huggingface.co/haqishen/Llama…