Phi-3.5-mini-instruct

mentions 3 type Organization feed RSS

// recent coverage 3 mentions

04:00

2026-08-20

machinebrief.com

artificial-intelligence

Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs

A new study from researchers including Shayan Shahrabi finds that bitsandbytes 4-bit (INT4/NF4) post-training quantization significantly amplifies proactive interference in large language models, redu…

22:56

2026-08-12

dev.to

large-language-models

What to Expect From Pure CPU-Only Local Inference

A developer explains that pure CPU-only local inference performance is fundamentally limited by memory bandwidth, not CPU cores, and provides a formula to calculate the theoretical maximum tokens per …

01:04

2026-06-25

discuss.huggingface.co

large-language-models

What prompt format/template should I use for training Unsloth/Phi-3.5-mini-instruct?

A developer is seeking advice on the optimal prompt format for training the Unsloth/Phi-3.5-mini-instruct model, currently using a custom template with JSON input and output fields. The choice of form…

// co-occurs with top 8 entities

Unsloth 1 Microsoft 1 Apple 1 M4 Pro 1 M4 Max 1 Hugging Face 1 Meta-Llama-3.1-8B-Instruct 1 Qwen2.5-Coder-14B-Instruct 1

// topics top 6 topics

large language models 3 developer tools 2 ai infrastructure 2 artificial intelligence 1 machine learning 1 ai research 1