mirror of
https://github.com/ollama/ollama.git
synced 2025-05-11 10:26:53 +02:00
58245413f4
feat: add new Ollama engine using ggml through cgo This change introduces a new way to run pretrained models. It introduces 3 high level interfaces and a bunch of smaller helper interfaces to facilitate this. - `model.Model` defines the interface for a model architecture. Models such as `llama` and `mllama`, which are provided as examples, can implement the model's forward propagation in the `Forward` method. This method will be called to generate completions. This interface can be found in `model/model.go` - `ml.Backend` defines the interface for a backend tensor library, in this case `ggml`. Among other things, a Backend is responsible for loading a pretrained model into hardware (GPU, CPU, etc) and providing an interface for Models to access loaded tensors. This interface can be found in `ml/backend.go` - `ml.Tensor` defines the interface for a tensor and tensor operations This is the first implementation of the new engine. Follow up PRs will implement more features: - non-greedy sampling (#8410) - integration with Ollama and KV caching (#8301) - more model support (#9080) with more coming soon Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com> |
||
|---|---|---|
| .. | ||
| sentencepiece | ||
| testdata | ||
| convert.go | ||
| convert_bert.go | ||
| convert_commandr.go | ||
| convert_gemma.go | ||
| convert_gemma2.go | ||
| convert_gemma2_adapter.go | ||
| convert_llama.go | ||
| convert_llama_adapter.go | ||
| convert_mixtral.go | ||
| convert_phi3.go | ||
| convert_qwen2.go | ||
| convert_test.go | ||
| fs.go | ||
| reader.go | ||
| reader_safetensors.go | ||
| reader_torch.go | ||
| sentencepiece_model.proto | ||
| tokenizer.go | ||
| tokenizer_spm.go | ||
| tokenizer_test.go | ||