🔄 In a Training Loop

Constantin

Alexandre-Numind

·

https://www.numind.ai/

AI & ML interests

Training AI models @Numind

Recent Activity

upvoted a paper 7 days ago

DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model

new activity 10 days ago

numind/NuExtract3:nuextract3 is down

upvoted a paper about 1 month ago

Improving Test-Time Scaling with Adaptive Looped Transformers

View all activity

Organizations

New activity in numind/NuExtract3 10 days ago

nuextract3 is down

#1 opened 11 days ago by

New activity in numind/NuExtract3 2 months ago

Add ExtractBench evaluation results

#4 opened 2 months ago by

boyang-runllama

New activity in numind/NuExtract3 4 months ago

Add olmOCR-bench old_scans result (community)

#3 opened 4 months ago by

New activity in numind/NuMarkdown-8B-Thinking 5 months ago

Fix base_model target (Qwen/Qwen2.5-VL-7B-Instruct)

#9 opened 5 months ago by

New activity in Qwen/Qwen3.5-35B-A3B 8 months ago

I would like a recommended training environment setup for the Qwen3.5-MoE model (e.g., Qwen3.5-35B-A3B, model_type: qwen3_5_moe).

#16 opened 8 months ago by

New activity in numind/NuMarkdown-8B-Thinking about 1 year ago

fixing numind.svg width

#1 opened about 1 year ago by

New activity in numind/NuExtract-tiny about 2 years ago

Add base_model metadata

#2 opened about 2 years ago by

New activity in numind/NuExtract over 2 years ago

How to provide examples in predict_NuExtract

#2 opened over 2 years ago by

New activity in numind/NuExtract-large over 2 years ago

NuExtract-large 7b and NuExtract 3.8B have same size model file

#4 opened over 2 years ago by

Error Sample Code

#2 opened over 2 years ago by

New activity in microsoft/Phi-3-small-8k-instruct over 2 years ago

RuntimeError: FlashAttention only support fp16 and bf16 data type during fine tuning.

#11 opened over 2 years ago by

faizsameerahmed96

New activity in numind/NuNER over 2 years ago

Change to non commercial license

#3 opened over 2 years ago by

New activity in numind/NuSentiment over 2 years ago

Change to non commercial license

#2 opened over 2 years ago by

[bot] Conversion to Parquet

#1 opened over 2 years ago by

parquet-converter

New activity in numind/NuNER over 2 years ago

[bot] Conversion to Parquet

#1 opened over 2 years ago by

parquet-converter

Librarian Bot: Add language metadata for dataset

#2 opened over 2 years ago by

New activity in numind/NuSentiment-multilingual almost 3 years ago

Adding `safetensors` variant of this model

#1 opened about 3 years ago by

New activity in numind/NuSentiment-multilingual about 3 years ago

Adding `safetensors` variant of this model

#2 opened about 3 years ago by

New activity in numind/NuSentiment over 3 years ago

Adding `safetensors` variant of this model

#1 opened over 3 years ago by