Modelfile
PulseAugur coverage of Modelfile — every cluster mentioning Modelfile across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Ollama bug misapplies Gemma 4 prompt templates
Ollama version 0.35.1 exhibits a subtle bug where it incorrectly selects the prompt template for Gemma 4 models. The software defaults to a 'small' template when a 'large' template is intended, particularly affecting mo…
-
Flash AI shell author forgoes fine-tuning due to Ollama infrastructure limits
The author of the Flash AI shell decided against fine-tuning their custom Onyx models due to infrastructure limitations. Flash relies on Ollama's cloud-based models for users without powerful local hardware, but this se…
-
Ollama's context length defaults are confusing and silently truncate conversations
Ollama's default context length is inconsistently documented and applied across different configurations. The documentation presents at least three conflicting default values: 2048 in the Modelfile reference, variable l…
-
Ollama create: A deep dive into building custom LLMs
Ollama's `create` command functions as a model compiler, taking a Modelfile to construct custom language models. It resolves the base model, processes instructions into content-addressed layers, and generates a manifest…