The Smol Training Playbook
📚
2.54k
The secrets to building world-class LLMs
Filippo B PRO
Filippo
AI & ML interests
GenAI, LLMs, VLMs, accelerated computing, information retrieval, workflows orchestration
Recent Activity
liked
a Space
about 1 month ago
HuggingFaceTB/smol-training-playbook
upvoted
an
article
about 2 months ago
Sentence Transformers is joining Hugging Face!
upvoted
an
article
5 months ago
OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models
Organizations
liked
a
Space
about 1 month ago
upvoted
an
article
about 2 months ago
Article
Sentence Transformers is joining Hugging Face!
•
85
upvoted
an
article
5 months ago
Article
OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models
•
50
upvoted
a
collection
6 months ago
upvoted
2
articles
7 months ago
Article
Vision Language Models (Better, faster, stronger)
- +3
•
568
Article
Vision Language Models Explained
•
496
upvoted
an
article
8 months ago
Article
Training and Finetuning Reranker Models with Sentence Transformers v4
•
175
updated
a
Space
9 months ago
updated
a
collection
9 months ago
liked
a
Space
10 months ago
updated
a
collection
10 months ago
upvoted
a
paper
10 months ago
upvoted
an
article
about 1 year ago
Article
Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably
•
26
updated
2
collections
about 1 year ago
upvoted
a
paper
about 1 year ago
reacted to
merve's
post with 🔥
about 1 year ago
Post
5711
I have put together a notebook on Multimodal RAG, where we do not process the documents with hefty pipelines but natively use:
- vidore/colpali for retrieval 📖 it doesn't need indexing with image-text pairs but just images!
- Qwen/Qwen2-VL-2B-Instruct for generation 💬 directly feed images as is to a vision language model with no processing to text!
I used ColPali implementation of the new 🐭 Byaldi library by @bclavie 🤗
https://github.com/answerdotai/byaldi
Link to notebook: https://github.com/merveenoyan/smol-vision/blob/main/ColPali_%2B_Qwen2_VL.ipynb
- vidore/colpali for retrieval 📖 it doesn't need indexing with image-text pairs but just images!
- Qwen/Qwen2-VL-2B-Instruct for generation 💬 directly feed images as is to a vision language model with no processing to text!
I used ColPali implementation of the new 🐭 Byaldi library by @bclavie 🤗
https://github.com/answerdotai/byaldi
Link to notebook: https://github.com/merveenoyan/smol-vision/blob/main/ColPali_%2B_Qwen2_VL.ipynb
upvoted
an
article
about 1 year ago
Article
ColPali: Efficient Document Retrieval with Vision Language Models 👀
•
303