A collection with text-classification and token-classification models for PII Protection
Alvaro Bartolome
alvarobartt
AI & ML interests
machine learning @huggingface (inference + cloud)
Recent Activity
liked a model about 1 hour ago
unsloth/Qwen3.6-35B-A3B-GGUF upvoted a changelog about 4 hours ago
Introducing Kernels reacted to sergiopaniego's post with 🤗 about 4 hours ago
Earlier this month, Apple introduced Simple Self-Distillation: a fine-tuning method that improves models on coding tasks just by sampling from the model and training on its own outputs with plain cross-entropy
And… it's already supported in TRL, built by Kashif Rasul. you can really feel the pace of development in the team 🐎
Paper by Ruixiang ZHANG, He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang at Apple 🍎
How it works: the model generates completions at a training-time temperature (T_train) with top_k/top_p truncation, then fine-tunes on them with plain cross-entropy. no labels or verifier needed
You can try it right away with this ready-to-run example (Qwen3-4B on rStar-Coder):
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd.py
or benchmark a checkpoint with the eval script:
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd_eval.py
One neat insight from the paper: T_train and T_eval compose into an effective T_eff = T_train × T_eval, so a broad band of configs works well. even very noisy samples still help
Want to dig deeper?
Paper: https://huggingface.co/papers/2604.01193
Trainer docs: https://huggingface.co/docs/trl/main/en/ssd_trainerOrganizations
![[INTERNAL] Hugging Face + Dell's profile picture](https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/otGPyK6OMlrQrkngKw4tJ.png)
This collection contains some Critique Models (CM) for LLM evaluation available in the HuggingFace Hub
Small to medium size datasets either: synthetically generated, labelled with AI Feedback (AIF), or both
Fine-tuned models to perform NER in Spanish using the framework SpanMarker and different encoders and datasets
Reading list to fully understand GPT (and GPT-2) and to be able to implement those from scratch
-
Neural Machine Translation of Rare Words with Subword Units
Paper • 1508.07909 • Published • 4 -
Attention Is All You Need
Paper • 1706.03762 • Published • 120 -
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Paper • 1810.04805 • Published • 26 -
Generating Wikipedia by Summarizing Long Sequences
Paper • 1801.10198 • Published • 3
Text-To-Image fine-tunes with Studio Ghibli style
Contains some information and experiments fine-tuning LLMs using 🤗 `trl.ORPOTrainer`
-
ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 72 -
HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
Text Generation • 141B • Updated • 127 • 269 -
alvarobartt/mistral-orpo-mix
Text Generation • 7B • Updated • 5 • 1 -
alvarobartt/Mistral-7B-v0.1-ORPO
Text Generation • 7B • Updated • 12 • 14
This collection contains the model weights for 7B LLMs for Apple's MLX framework. Find more information at https://github.com/ml-explore/mlx
This collection contains some datasets for LLM evaluation in Spanish, from nlp.uoregon.edu, translated using ChatGPT (including English counterparts)
A collection with text-classification and token-classification models for PII Protection
Text-To-Image fine-tunes with Studio Ghibli style
This collection contains some Critique Models (CM) for LLM evaluation available in the HuggingFace Hub
Contains some information and experiments fine-tuning LLMs using 🤗 `trl.ORPOTrainer`
-
ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 72 -
HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
Text Generation • 141B • Updated • 127 • 269 -
alvarobartt/mistral-orpo-mix
Text Generation • 7B • Updated • 5 • 1 -
alvarobartt/Mistral-7B-v0.1-ORPO
Text Generation • 7B • Updated • 12 • 14
Small to medium size datasets either: synthetically generated, labelled with AI Feedback (AIF), or both
This collection contains the model weights for 7B LLMs for Apple's MLX framework. Find more information at https://github.com/ml-explore/mlx
Fine-tuned models to perform NER in Spanish using the framework SpanMarker and different encoders and datasets
This collection contains some datasets for LLM evaluation in Spanish, from nlp.uoregon.edu, translated using ChatGPT (including English counterparts)
Reading list to fully understand GPT (and GPT-2) and to be able to implement those from scratch
-
Neural Machine Translation of Rare Words with Subword Units
Paper • 1508.07909 • Published • 4 -
Attention Is All You Need
Paper • 1706.03762 • Published • 120 -
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Paper • 1810.04805 • Published • 26 -
Generating Wikipedia by Summarizing Long Sequences
Paper • 1801.10198 • Published • 3