Abhishek Thakur's picture

Abhishek Thakur

abhishek

AI & ML interests

None yet

Recent Activity

Articles

Organizations

Hugging Face's profile picture Competitions's profile picture AutoNLP's profile picture ๐ŸงจDiffusers's profile picture Spaces-explorers's profile picture AutoTrain Projects's profile picture Bohemian Visual Recognition Alliance's profile picture Evaluation on the Hub's profile picture Generative News's profile picture HuggingFaceM4's profile picture ChaBuD Team's profile picture (De)fusing's profile picture Artificio's profile picture hyphen's profile picture Hugging Face H4's profile picture Data-Driven Science's profile picture Diffusers Pipelines Library for Stable Diffusion's profile picture HuggingFace Doc Builds's profile picture Blog-explorers's profile picture Wyze Labs's profile picture OpenDriveLab's profile picture Hugging Face TB Research's profile picture llm-sci-exam-anrut's profile picture Media Party 2023's profile picture Enterprise Explorers's profile picture fdsgfdsgfd's profile picture Test's profile picture Sellence's profile picture GNR8's profile picture Voxel51's profile picture Urban Scene Modeling Competition CVPR 2024 (Image Track)'s profile picture Challenge's profile picture Social Post Explorers's profile picture flux train's profile picture OpenPhotoHeadShot's profile picture open/ acc's profile picture

abhishek's activity

reacted to takarajordan's post with ๐Ÿ”ฅ 13 days ago
view post
Post
2199
I'm super excited to release my first open-source text dataset:

WorldScenario 20K is a novel dataset of 20,000 synthetically generated multi-stakeholder scenarios designed to simulate real-world decision-making processes. Each scenario explores a unique environmental, societal, or economic issue.

I used the brand new meta-llama/Llama-3.3-70B-Instruct model to generate this dataset and I put the dataset through some post processing to clean and evaluate the dataset for diversity.

I'd appreciate some feedback and thoughts on my new release! Thanks!

takarajordan/WorldScenario_20K
ยท
posted an update 25 days ago
view post
Post
1617
๐ŸŽ‰ SUPER BLACK FRIDAY DEAL ๐ŸŽ‰

Train almost any model on a variety of tasks such as llm finetuning, text classification/regression, summarization, question answering, image classification/regression, object detection, tabular data, etc for FREE using AutoTrain locally. ๐Ÿ”ฅ
https://github.com/huggingface/autotrain-advanced
replied to their post about 1 month ago
replied to their post about 1 month ago
reacted to their post with ๐Ÿ‘ about 2 months ago
view post
Post
5410
INTRODUCING Hugging Face AutoTrain Client ๐Ÿ”ฅ
Fine-tuning models got even easier!!!!
Now you can fine-tune SOTA models on all compatible dataset-model pairs on Hugging Face Hub using Python on Hugging Face Servers. Choose from a number of GPU flavors, millions of models and dataset pairs and 10+ tasks ๐Ÿค—

To try, install autotrain-advanced using pip. You can ignore dependencies and install without --no-deps and then you'd need to install some dependencies by hand.

"pip install autotrain-advanced"

Github repo: https://github.com/huggingface/autotrain-advanced
  • 6 replies
ยท
posted an update about 2 months ago
view post
Post
5410
INTRODUCING Hugging Face AutoTrain Client ๐Ÿ”ฅ
Fine-tuning models got even easier!!!!
Now you can fine-tune SOTA models on all compatible dataset-model pairs on Hugging Face Hub using Python on Hugging Face Servers. Choose from a number of GPU flavors, millions of models and dataset pairs and 10+ tasks ๐Ÿค—

To try, install autotrain-advanced using pip. You can ignore dependencies and install without --no-deps and then you'd need to install some dependencies by hand.

"pip install autotrain-advanced"

Github repo: https://github.com/huggingface/autotrain-advanced
  • 6 replies
ยท
reacted to their post with ๐Ÿ‘ 2 months ago
posted an update 2 months ago
posted an update 4 months ago
posted an update 4 months ago
view post
Post
1854
๐Ÿšจ NEW TASK ALERT ๐Ÿšจ
Extractive Question Answering: because sometimes generative is not all you need ๐Ÿ˜‰
AutoTrain is the only open-source, no code solution to offer so many tasks across different modalities. Current task count: 23 ๐Ÿš€
Check out the blog post on getting started with this task: https://huggingface.co./blog/abhishek/extractive-qa-autotrain
replied to their post 7 months ago
reacted to their post with ๐Ÿš€ 7 months ago
posted an update 7 months ago
reacted to their post with ๐Ÿ”ฅ 8 months ago
view post
Post
2935
๐Ÿšจ NEW TASK ALERT ๐Ÿšจ
๐ŸŽ‰ AutoTrain now supports Object Detection! ๐ŸŽ‰
Transform your projects with these powerful new features:
๐Ÿ”น Fine-tune any supported model from the Hugging Face Hub
๐Ÿ”น Seamless logging with TensorBoard or W&B
๐Ÿ”น Support for local and hub datasets
๐Ÿ”น Configurable training for tailored results
๐Ÿ”น Train locally or leverage Hugging Face Spaces
๐Ÿ”น Deployment-ready with API inference or Hugging Face endpoints
AutoTrain: https://hf.co/autotrain
posted an update 8 months ago
view post
Post
2935
๐Ÿšจ NEW TASK ALERT ๐Ÿšจ
๐ŸŽ‰ AutoTrain now supports Object Detection! ๐ŸŽ‰
Transform your projects with these powerful new features:
๐Ÿ”น Fine-tune any supported model from the Hugging Face Hub
๐Ÿ”น Seamless logging with TensorBoard or W&B
๐Ÿ”น Support for local and hub datasets
๐Ÿ”น Configurable training for tailored results
๐Ÿ”น Train locally or leverage Hugging Face Spaces
๐Ÿ”น Deployment-ready with API inference or Hugging Face endpoints
AutoTrain: https://hf.co/autotrain
posted an update 8 months ago
view post
Post
3062
๐Ÿš€๐Ÿš€๐Ÿš€๐Ÿš€ Introducing AutoTrain Configs! ๐Ÿš€๐Ÿš€๐Ÿš€๐Ÿš€
Now you can train models using yaml config files! ๐Ÿ’ฅ These configs are easy to understand and are not at all overwhelming. So, even a person with almost zero knowledge of machine learning can train state of the art models without writing any code. Check out example configs in the config directory of autotrain-advanced github repo and feel free to share configs by creating a pull request ๐Ÿค—
Github repo: https://github.com/huggingface/autotrain-advanced
  • 2 replies
ยท
reacted to their post with ๐Ÿ˜Ž 8 months ago
posted an update 8 months ago
reacted to their post with ๐Ÿš€ 8 months ago
view post
Post
2371
Trained another version of llama3-8b-instruct which beats the base model. This time without losing too many points on gsm8k benchmark. Again, using AutoTrain ๐Ÿ’ฅ pip install autotrain-advanced
Trained model: abhishek/autotrain-llama3-orpo-v2
  • 1 reply
ยท
posted an update 8 months ago
view post
Post
2371
Trained another version of llama3-8b-instruct which beats the base model. This time without losing too many points on gsm8k benchmark. Again, using AutoTrain ๐Ÿ’ฅ pip install autotrain-advanced
Trained model: abhishek/autotrain-llama3-orpo-v2
  • 1 reply
ยท