mirror of
https://github.com/ollama/ollama.git
synced 2026-10-25 04:51:59 +00:00
66c3238b3d
model is one package with three jobs: the contract between the runner and the architectures, the opened checkpoint, and building nn layers from checkpoint tensors. Its files did not say which was which. base.go carried the folded package's name over the interfaces and the registry, root.go held the safetensors header scan next to Root, and quant.go mixed the nvfp4 global-scale helpers with quant parameter resolution. base.go becomes model.go, named for what it holds. root.go keeps Root and Open; TensorQuantInfo and the header scan join quant.go, so everything the checkpoint says about quantization is read and resolved in one file. The global-scale helpers move to globalscale.go with their tests. Root.Close, a no-op with one caller, goes. No code changes otherwise. |
||
|---|---|---|
| .. | ||
| architectures | ||
| audio | ||
| cohere2_moe | ||
| dflash | ||
| gemma4 | ||
| glimmer | ||
| glm4_moe_lite | ||
| laguna | ||
| llama | ||
| nemotron_h | ||
| qwen3 | ||
| qwen3_5 | ||
| qwen3_5_moe | ||
| qwen4_exp | ||
| embedding.go | ||
| embedding_test.go | ||
| globalscale.go | ||
| globalscale_test.go | ||
| linear.go | ||
| media.go | ||
| model.go | ||
| quant.go | ||
| root.go | ||