27 12 319

Carlo Moro

cnmoro

https://www.linkedin.com/in/carlo-moro-4a20a7132/

cnmoro

AI & ML interests

I like small & fast models Trabalhando nos menores modelos em português que existem https://ko-fi.com/cnmoro

Recent Activity

liked a model about 10 hours ago

teapotai/teapotllm

reacted to tomaarsen's post with 🔥 1 day ago

‼️Sentence Transformers v4.0 is out! You can now train and finetune reranker models with multi-GPU training, bf16 support, loss logging, callbacks & much more. I also prove that finetuning on your domain helps much more than you might think. 1️⃣ Reranker Training Refactor Reranker models can now be trained using an extensive trainer with a lot of powerful features: - MultiGPU Training (Data Parallelism (DP) and Distributed Data Parallelism (DDP)) - bf16 training support; loss logging - Evaluation datasets + evaluation loss - Improved callback support + an excellent Weights & Biases integration - Gradient checkpointing, gradient accumulation - Model card generation - Resuming from a training checkpoint without performance loss - Hyperparameter Optimization and much more! Read my detailed blogpost to learn about the components that make up this new training approach: https://huggingface.co/blog/train-reranker Notably, the release is fully backwards compatible: all deprecations are soft, meaning that they still work but emit a warning informing you how to upgrade. 2️⃣ New Reranker Losses - 11 new losses: - 2 traditional losses: BinaryCrossEntropy and CrossEntropy - 2 distillation losses: MSE and MarginMSE - 2 in-batch negatives losses: MNRL (a.k.a. InfoNCE) and CMNRL - 5 learning to rank losses: Lambda, p-ListMLE, ListNet, RankNet, ListMLE 3️⃣ New Reranker Documentation - New Training Overview, Loss Overview, API Reference docs - 5 new, 1 refactored training examples docs pages - 13 new, 6 refactored training scripts - Migration guides (2.x -> 3.x, 3.x -> 4.x) 4️⃣ Blogpost Alongside the release, I've written a blogpost where I finetune ModernBERT on a generic question-answer dataset. My finetunes easily outperform all general-purpose reranker models, even models 4x as big. Finetuning on your domain is definitely worth it: https://huggingface.co/blog/train-reranker See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/v4.0.1

updated a dataset 1 day ago

cnmoro/reasoning-v1-20m-portuguese

View all activity

Organizations

cnmoro's activity

New activity in BlinkDL/rwkv7-g1 9 days ago

ONNX

#2 opened 9 days ago by

cnmoro

New activity in cnmoro/Qwen2.5-0.5B-Portuguese-v1 25 days ago

Dúvidas sobre steps e datasets.

#1 opened 29 days ago by

martignago

New activity in allenai/olmOCR-7B-0225-preview 29 days ago

please create a quantized version, preferably using bitsandbytes!

#3 opened about 1 month ago by

ctranslate2-4you

New activity in HuggingFaceTB/SmolVLM-256M-Instruct 2 months ago

ONNX Demo code

#4 opened 2 months ago by

cnmoro

New activity in Snowflake/snowflake-arctic-embed-m-v2.0 2 months ago

can the medium model run on CPU

#5 opened 3 months ago by

ctranslate2-4you

New activity in cnmoro/static-retrieval-distilbert-ptbr 2 months ago

Performance

#1 opened 2 months ago by

tomaarsen

New activity in bhavnicksm/dark-potion-base-150M 2 months ago

Base Model

#1 opened 2 months ago by

cnmoro

New activity in jinaai/jina-embeddings-v3 6 months ago

Model seems to be incredibly slow on CPU

#34 opened 6 months ago by

adi751

New activity in arcee-ai/arcee-lite 8 months ago

Really nice little model

#2 opened 8 months ago by

cnmoro

New activity in lunahr/SystemGemma2-2b-it 8 months ago

Hallucination

#2 opened 8 months ago by

cnmoro

New activity in QuantFactory/InstructLM-500M-GGUF 9 months ago

Prompt template

#1 opened 9 months ago by

cnmoro

New activity in uygarkurt/llama-3-merged-linear 10 months ago

Merge procedure

#1 opened 10 months ago by

cnmoro

New activity in recogna-nlp/phibode_1_5_ultraalpaca 10 months ago

Prompt template

#2 opened 10 months ago by

cnmoro

New activity in TroyDoesAI/Mermaid-Llama-3-5B-Pruned 11 months ago

Pruning

#1 opened 11 months ago by

cnmoro

New activity in refuelai/Llama-3-Refueled 11 months ago

Template

#1 opened 11 months ago by

cnmoro

New activity in botbot-ai/CabraLlama3-8b 11 months ago

Parabéns pelo trabalho

#2 opened 11 months ago by

alexspf

New activity in adalbertojunior/Llama-3-8B-Dolphin-Portuguese 11 months ago

Chat template.

#1 opened 11 months ago by

arthrod

New activity in cnmoro/Mistral-7B-Portuguese 12 months ago

Fixing some errors of the leaderboard evaluation results in the ModelCard yaml

#5 opened 12 months ago by

leaderboard-pt-pr-bot

Adding the Open Portuguese LLM Leaderboard Evaluation Results

#2 opened 12 months ago by

leaderboard-pt-pr-bot

New activity in cnmoro/Mistral-7B-Portuguese about 1 year ago

como fez o fine-tuning ?

#1 opened about 1 year ago by

rickfalcao