john smith

k249's activity

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

upvoted a collection 9 days ago

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Collection

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 34 items • Updated 3 days ago • 11

upvoted 2 collections 22 days ago

Clara-Medical

Collection

NVIDIA Clara Open Models for medical imaging AI: segment, generate, and reason across CT, MRI, and X-ray. Built on MONAI by NVIDIA. • 7 items • Updated 3 days ago • 10

Inference Optimized Checkpoints (with Model Optimizer)

Collection

A collection of generative models quantized and optimized for inference with Model Optimizer. • 46 items • Updated 3 days ago • 66

upvoted an article 22 days ago

view article

Article

Ellora: Enhancing LLMs with LoRA - Standardized Recipes for Capability Enhancement

• 

24 days ago

•

12

upvoted 2 collections 29 days ago

Qwen 3 / 2.5 Reasoning/Thinking REG + MOEs.

Collection

Qwen 3 / 2.5 Reasoning/Thinking models in both regular and MOE configuration built by me. Source code links also below too. • 185 items • Updated 3 days ago • 9

Clara-Molecular

Collection

NVIDIA Clara Models for Molecular Science • 9 items • Updated 3 days ago • 5

upvoted 3 collections about 1 month ago

DistilQwen

Collection

All DistilQwen models and datasets • 22 items • Updated Oct 9 • 4

MXFP4 Hybrid GGUF

Collection

MXFP4 hybrid GGUF models getting... well.. Getting some interesting results. THIS IS NOW SURPASSED VASTLY BY MAGIC QUANT COLLECTION! • 11 items • Updated 26 days ago • 4

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 19 items • Updated 7 days ago • 65

upvoted a paper about 1 month ago

OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

Paper • 2508.01630 • Published Aug 3 • 12

upvoted 3 collections 3 months ago

Granite 4.0 Language Models

Collection

13 items • Updated Nov 17 • 198

Medical Data

Collection

32 items • Updated Aug 31 • 2

Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10 • 211