L

@local-builds

Member since 2024-12 · 1 adapter · 5 notes

Published adapters

text-generation members

CodeLlama 13B Python Refactor

codellama/CodeLlama-13b-Python-hf

v2.0.1 gguf 7424 MiB

Community notes

Inference & Serving 6 min

Serving Four LoRA Adapters from One Base Model

A practical LoRADock note covering inputs, validation, tradeoffs, and release criteria for serving four lora adapters from one base model.

Inference & Serving 6 min

Safetensors or GGUF: What Worked Better on My Small Server

A practical LoRADock note covering inputs, validation, tradeoffs, and release criteria for safetensors or gguf: what worked better on my small server.

Failures & Postmortems 4 min

A Rank-64 Experiment That Added Size but No Quality

A practical LoRADock note on inputs, validation, tradeoffs, and release decisions for a rank-64 experiment that added size but no quality.

Training Logs 5 min

My Default LoRA Configuration for Small Instruction Datasets

A conservative starting configuration for small instruction datasets, including parameter failure signals, tuning order, and registry documentation for repeatable LoRA runs.

Inference & Serving 6 min

Running a Quantized Text Adapter on a 16 GB Machine

A practical LoRADock note covering inputs, validation, tradeoffs, and release criteria for running a quantized text adapter on a 16 gb machine.