3 25

Jhonata

JJhooww

AI & ML interests

None yet

Recent Activity

updated a model about 2 months ago

JJhooww/Mistral-7B-v0.2-Instruction

updated a model about 2 months ago

JJhooww/Mistral-7B-v0.2-Base_ptbr

View all activity

Organizations

None yet

JJhooww's activity

updated 2 models about 2 months ago

JJhooww/Mistral-7B-v0.2-Instruction

Text Generation • Updated Oct 25 • 345

JJhooww/Mistral-7B-v0.2-Base_ptbr

Text Generation • Updated Oct 25 • 35 • 1

liked a Space 6 months ago

Running on A10G

1.04k

🦙

GGUF My Repo

updated a model 6 months ago

JJhooww/Classificador_de_prompt

Text Classification • Updated Jun 15 • 4

liked a dataset 6 months ago

adalbertojunior/Guara

Viewer • Updated Jun 8 • 958k • 69 • 7

liked 2 models 7 months ago

unsloth/mistral-7b-v0.3-bnb-4bit

Text Generation • Updated 27 days ago • 63.4k • 13

adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3

Text Generation • Updated Sep 2 • 182 • 7

liked 7 models 8 months ago

liked 2 datasets 8 months ago

bastao/VeraCruz_PT-BR

Viewer • Updated 3 days ago • 190M • 1.73k • 10

rhaymison/ultrachat-easy-use

Viewer • Updated Apr 3 • 1.62M • 49 • 2

liked a model 9 months ago

22h/open-cabrita3b

Text Generation • Updated Mar 12 • 784 • 20

reacted to davanstrien's post with 👍 9 months ago

Post

KTO offers an easier way to preference train LLMs (only 👍👎 ratings are required). As part of #DataIsBetterTogether, I've written a tutorial on creating a preference dataset using Argilla and Spaces.

Using this approach, you can create a dataset that anyone with a Hugging Face account can contribute to 🤯

See an example of the kind of Space you can create following this tutorial here: davanstrien/haiku-preferences

🆕 New tutorial covers:
💬 Generating responses with open models
👥 Collecting human feedback (do you like this model response? Yes/No)
🤖 Preparing a TRL-compatible dataset for training aligned models

Check it out here: https://github.com/huggingface/data-is-better-together/tree/main/kto-preference

2 replies