Oliver Holworthy

nvidia-oliver-holworthy's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in nvidia/llama-nemotron-embed-1b-v2 2 days ago

Replace custom LlamaBidirectionalModel with is_causal=false config

#21 opened 2 days ago by

nvidia-oliver-holworthy

New activity in nvidia/NVIDIA-Nemotron-Parse-v1.2 3 days ago

Update with support for transformers 5.x compatibility

1

#4 opened 3 days ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-embed-vl-1b-v2 15 days ago

Add vLLM Usage example to README

#7 opened 15 days ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-embed-1b-v2 15 days ago

Add vLLM Usage example to README

#20 opened 15 days ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-rerank-1b-v2 16 days ago

Add rope_theta to rope_scaling for transformers 5.4+ compatibility

#14 opened 16 days ago by

nvidia-oliver-holworthy

New activity in nvidia/omni-embed-nemotron-3b 16 days ago

Integrate with Sentence Transformers v5.4

🚀 1

#3 opened 18 days ago by

tomaarsen

New activity in nvidia/llama-nemotron-rerank-vl-1b-v2 16 days ago

Integrate with Sentence Transformers v5.4

#9 opened 18 days ago by

tomaarsen

New activity in nvidia/llama-nemotron-embed-vl-1b-v2 16 days ago

Integrate with Sentence Transformers v5.4

5

#6 opened 18 days ago by

tomaarsen

New activity in nvidia/llama-nemotron-rerank-vl-1b-v2 19 days ago

Add vLLM usage examples

#8 opened 19 days ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-rerank-1b-v2 19 days ago

Fix vLLM usage: add required score template for correct reranking

#13 opened 19 days ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-embed-1b-v2 27 days ago

Add rope_theta to rope_scaling for transformers 5.4+ compatibility

#19 opened 27 days ago by

nvidia-oliver-holworthy

New activity in nvidia/Retrieval-Synthetic-NVDocs-v1 about 1 month ago

Add sample corpus for embedding recipe quick start

#9 opened about 1 month ago by

nvidia-oliver-holworthy

published an article about 1 month ago

view article

Article

Build a Domain-Specific Embedding Model in Under a Day

• 

Mar 20

•

70

New activity in nvidia/llama-nemotron-rerank-vl-1b-v2 about 2 months ago

Consolidate max sequence length to tokenizer model_max_length

#6 opened about 2 months ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-rerank-1b-v2 about 2 months ago

VLLM Support

2

#7 opened 5 months ago by

salmankhanpm

Add vLLM usage

#12 opened about 2 months ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-embed-1b-v2 about 2 months ago

Update vLLM usage docs: remove config_vllm.json overwrite, relax version pin, and clarify minimal required flags

#18 opened about 2 months ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-embed-vl-1b-v2 2 months ago

Add convenience options to processor methods

1

#3 opened 4 months ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-rerank-vl-1b-v2 2 months ago

Add convenience options to processor methods

#5 opened 2 months ago by

nvidia-oliver-holworthy

New activity in nvidia/llama-nemotron-embed-vl-1b-v2 2 months ago

Use default attention implementation with option to override

🔥 1

2

#2 opened 4 months ago by

nvidia-oliver-holworthy