ollama

Commit Graph

Author	SHA1	Message	Date
Daniel Hiltgen	424810450f	Move quantization to new backend (#10363 ) * Move quantization logic to GGML via new backend This moves the model aware logic to Go code and calls GGMLs quantization code for model creation. * Remove "add model quantizations" This is no longer needed now that quantization is implemented in Go+GGML code directly.	11 months ago
Michael Yang	58245413f4	next ollama runner (#7913 ) 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>	1 year ago
Patrick Devine	2539f2dbf9	Fix absolute path names + gguf detection (#8428 )	1 year ago
Patrick Devine	86a622cbdc	Update the /api/create endpoint to use JSON (#7935 ) Replaces `POST /api/create` to use JSON instead of a Modelfile. This is a breaking change.	1 year ago
Michael Yang	413ae39f3c	update templates to use messages	2 years ago
Jeffrey Morgan	47fa0839b9	server: clean up route names for consistency (#6524 )	2 years ago
Michael Yang	a091fadfda	use testing tempdirs	2 years ago
Michael Yang	b732beba6a	lint	2 years ago
Michael Yang	df993fa37b	comments	2 years ago
Michael Yang	5e9db9fb0b	refactor convert	2 years ago
Michael Yang	1954ec5917	uint64	2 years ago
Josh	e8b954c646	server: validate template (#5734 ) add template validation to modelfile	2 years ago
Michael Yang	4a565cbf94	add chat and generate tests with mock runner	2 years ago
Michael Yang	ebc529cbb3	autodetect stop parameters from template	2 years ago
Michael Yang	57ec6901eb	revert embedded templates to use prompt/response This reverts commit `19753c18c0`. for compat. messages will be added at a later date	2 years ago
Michael Yang	41be28096a	add system prompt to first legacy template	2 years ago
Michael Yang	fb6cbc02fb	update named templates	2 years ago
Patrick Devine	94618b2365	add OLLAMA_MODELS to envconfig (#5029 )	2 years ago
Michael Yang	c16f8af911	fix: multiple templates when creating from model multiple templates may appear in a model if a model is created from another model that 1) has an autodetected template and 2) defines a custom template	2 years ago
Michael Yang	030e765e76	fix create model when template detection errors	2 years ago
Michael Yang	d61ef8b954	update create handler to use model.Name	2 years ago
Michael Yang	c5e892cb3e	update tests	2 years ago

25 Commits (2c776f07805022221e7640a643777818528d0a27)