🔄 In a Training Loop

gbhf

gbuzhf

·

https://github.com/gbgh1/context-governor

gbgh1

AI & ML interests

None yet

Recent Activity

new activity about 1 hour ago

gbuzhf/Nex-N2.5-mini-Sangreal-ICE:Chat template fixed.

new activity about 1 hour ago

gbuzhf/Nex-N2.5-mini-OrcaRouter-Sangreal-ICE:Chat template fixed.

updated a model about 4 hours ago

gbuzhf/Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE-GGUF

View all activity

Organizations

None yet

upvoted 3 papers 22 days ago

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

Paper • 2608.03796 • Published Aug 4 • 20

LLM Compression by Block Removal with Constrained Binary Optimization

Paper • 2602.00161 • Published Jun 17 • 9

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

Paper • 2608.20953 • Published Aug 21 • 14

upvoted an article 24 days ago

Article

Per-tensor layout maps for GGUF quantization

bartowski

•

24 days ago

• 41

upvoted 2 collections 25 days ago

Tiel-Coder-35B-A3B

A dedicated coder improving on Ornith1.5 without fine tuning. • 6 items • Updated 27 days ago • 8

Cyber-Tiel-Coder-35B-A3B

The improved an uncensored Tiel-Coder • 6 items • Updated 26 days ago • 16

upvoted an article about 1 month ago

Article

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

MultiverseComputingCAI

•

Aug 25

• 70

upvoted a collection about 2 months ago

Unsloth Dynamic 3.0 Quants

Introducing Dynamic V3.0 quants, our new SOTA quantization methodology. • 1 item • Updated Aug 26 • 76

upvoted a collection 3 months ago

APEX Quants (GGUF)

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 48 items • Updated 23 days ago • 149