JT

jtvino's activity

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

New activity in nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 13 days ago

Tool Calling Catastrophic Forgetfulness

#11 opened 13 days ago by

jtvino

New activity in google/diffusiongemma-26B-A4B-it 15 days ago

VLLM setup? Getting malformed responses. What is correct configuration

3

#11 opened 22 days ago by

jtvino

liked a model 16 days ago

LiquidAI/LFM2.5-350M

Text Generation • 0.4B • Updated 6 days ago • 80.8k • 364

New activity in nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 28 days ago

Tool Calling Failure because of missing '}'

2

#8 opened 28 days ago by

jtvino

liked 3 models about 1 month ago

nvidia/Cosmos3-Nano

16B • Updated 15 days ago • 173k • 284

nvidia/Cosmos3-Super

65B • Updated 15 days ago • 80.1k • 193

prism-ml/bonsai-image-binary-4B-unpacked

Text-to-Image • Updated Jun 1 • 111 • 26

New activity in google/gemma-4-31B-it about 1 month ago

Thinking erratic at 30000+ context

4

#76 opened 3 months ago by

JeslynMcKenzie

liked a model about 2 months ago

CohereLabs/command-a-plus-05-2026-bf16

Image-Text-to-Text • 219B • Updated 23 days ago • 10.1k • • 139

New activity in nvidia/Nemotron-Labs-Diffusion-14B about 2 months ago

VLLM?

➕ 5

1

#2 opened about 2 months ago by

jtvino

New activity in google/gemma-4-31B-it about 2 months ago

Drops in performance randomly VLLM on H200 and B200 with 2 GPUs

#104 opened about 2 months ago by

jtvino

liked 2 models about 2 months ago

ibm-granite/granite-speech-4.1-2b-nar

Feature Extraction • 2B • Updated 20 days ago • 222k • 57

Zyphra/ZAYA1-74B-preview

75B • Updated 12 days ago • 210 • 46

liked a model 2 months ago

RedHatAI/gemma-4-31B-it-FP8-block

Image-Text-to-Text • 31B • Updated 19 days ago • 3.8M • 39

New activity in SWE-bench/SWE-bench_Verified 2 months ago

No Gemma4

👍 1

#5 opened 2 months ago by

jtvino

New activity in nvidia/Efficient-DLM-8B 2 months ago

Scaling to bigger models and MOE?

#1 opened 2 months ago by

jtvino

liked 3 models 2 months ago

nvidia/Efficient-DLM-8B

Text Generation • 8B • Updated May 3 • 444 • 13

ibm-granite/granite-embedding-311m-multilingual-r2

Feature Extraction • 0.3B • Updated May 18 • 213k • • 108

nvidia/nemotron-ocr-v2

Image-to-Text • Updated May 22 • 11.8k • 225

New activity in RedHatAI/gemma-4-31B-it-speculator.dflash 2 months ago

No thinking in training datset?

➕ 2

#6 opened 2 months ago by

jtvino