Oliver Holworthy
AI & ML interests
None yet
Recent Activity
new activity about 10 hours ago
nvidia/Nemotron-3-Embed-1B-NVFP4:Clarify vLLM CUDA graph sizing and refine model card details new activity about 11 hours ago
nvidia/Nemotron-3-Embed-1B-NVFP4:Document expected Transformers warning new activity about 15 hours ago
nvidia/Nemotron-3-Embed-8B-BF16:Document expected RoPE compatibility warningOrganizations
Clarify vLLM CUDA graph sizing and refine model card details
#3 opened about 12 hours ago
by
oliverholworthy
Document expected Transformers warning
#2 opened about 12 hours ago
by
oliverholworthy
Document expected RoPE compatibility warning
#2 opened about 15 hours ago
by
oliverholworthy
Document expected RoPE compatibility warning
#2 opened about 15 hours ago
by
oliverholworthy
Clarify CUDA graph capture sizing
#1 opened about 15 hours ago
by
oliverholworthy
Improve metadata, language name, small typos, code snippet output formatting
3
#1 opened about 21 hours ago
by
tomaarsen
Avoid deprecated bidirectional mask embed keyword
#2 opened about 2 months ago
by
oliverholworthy
Avoid deprecated bidirectional mask embed keyword
#1 opened about 2 months ago
by
oliverholworthy
Avoid deprecated bidirectional mask embed keyword
#9 opened about 2 months ago
by
oliverholworthy
Avoid deprecated bidirectional mask embed keyword
#10 opened about 2 months ago
by
oliverholworthy
Avoid deprecated bidirectional mask embed keyword
#15 opened about 2 months ago
by
oliverholworthy
Use positional bidirectional mask helper call
1
#22 opened about 2 months ago
by
oliverholworthy
transformers code fixes
1
#2 opened 4 months ago
by
pszemraj
How can I run this model on a more recent version of transformers?
1
#7 opened 5 months ago
by
rsbdev
Add golden tests and latest runtime support for Nemotron Parse v1.1
#8 opened 2 months ago
by
oliverholworthy
Normalize Nemotron Parse images in the processor for vLLM compatibility
1
#6 opened 2 months ago
by
oliverholworthy
Add chat template and task instructions for vLLM embedding requests
#8 opened 3 months ago
by
oliverholworthy
Replace custom LlamaBidirectionalModel with is_causal=false config
#21 opened 3 months ago
by
oliverholworthy
Update with support for transformers 5.x compatibility
1
#4 opened 3 months ago
by
oliverholworthy
Add vLLM Usage example to README
#7 opened 3 months ago
by
oliverholworthy