mirror of
https://github.com/ollama/ollama.git
synced 2026-03-28 03:08:44 +07:00
33ee7168ba
* WIP - MLX backend with gemma3 * MLX: add cmake and go tag build toggles To build the new MLX backend code: cmake --preset MLX cmake --build --preset MLX --parallel cmake --install build --component MLX go build -tags mlx . Note: the main.go entrypoint for the MLX engine will change in a follow up commit. * add experimental image generation runtime * add experimental image generation runtime * MLX: wire up cuda build for linux * MLX: get dependencies correct and dedup This is still too large for a unified github artifact, but is now "correct" for the mlx_cuda_v13 directory. * fix relative link bug in dedup * Add darwin build and readme * add go build tag for mlx dependent code and wire up build_darwin.sh * lint cleanup * macos: build mlx for x86 This will be CPU only. * cuda build instructions and fix drift from mlx bump * stale comment * Delete agent helper doc * Clean up readme.md * Revise README for tokenizer clarity and details Updated README to clarify tokenizer functionality and removed correctness section. --------- Co-authored-by: jmorganca <jmorganca@gmail.com>
73 lines
1.4 KiB
Go
73 lines
1.4 KiB
Go
package rope
|
|
|
|
import "github.com/ollama/ollama/x/ml"
|
|
|
|
// Options contains optional parameters for RoPE function
|
|
type Options struct {
|
|
Type int
|
|
Factors ml.Tensor
|
|
|
|
// YaRN options
|
|
YaRN struct {
|
|
OriginalContextLength int
|
|
ExtrapolationFactor,
|
|
AttentionFactor,
|
|
BetaFast,
|
|
BetaSlow float32
|
|
}
|
|
|
|
// MRoPE options
|
|
MRoPE struct {
|
|
Sections []int
|
|
}
|
|
}
|
|
|
|
// WithTypeNeoX sets RoPE type to NeoX
|
|
func WithTypeNeoX() func(*Options) {
|
|
return func(opts *Options) {
|
|
opts.Type = 2
|
|
}
|
|
}
|
|
|
|
// WithFactors sets custom rope factors
|
|
func WithFactors(factors ml.Tensor) func(*Options) {
|
|
return func(opts *Options) {
|
|
if factors != nil {
|
|
opts.Factors = factors
|
|
}
|
|
}
|
|
}
|
|
|
|
// WithOriginalContextLength sets a custom context length
|
|
func WithOriginalContextLength(n int) func(*Options) {
|
|
return func(opts *Options) {
|
|
opts.YaRN.OriginalContextLength = n
|
|
}
|
|
}
|
|
|
|
func WithExtrapolationFactor(extrapolationFactor float32) func(*Options) {
|
|
return func(opts *Options) {
|
|
opts.YaRN.ExtrapolationFactor = extrapolationFactor
|
|
}
|
|
}
|
|
|
|
func WithAttentionFactor(attentionFactor float32) func(*Options) {
|
|
return func(opts *Options) {
|
|
opts.YaRN.AttentionFactor = attentionFactor
|
|
}
|
|
}
|
|
|
|
func WithMRoPE(sections []int) func(*Options) {
|
|
return func(opts *Options) {
|
|
opts.Type |= 1 << 3
|
|
opts.MRoPE.Sections = sections
|
|
}
|
|
}
|
|
|
|
func WithInterleaveMRoPE(sections []int) func(*Options) {
|
|
return func(opts *Options) {
|
|
opts.Type |= 1<<3 | 1<<5
|
|
opts.MRoPE.Sections = sections
|
|
}
|
|
}
|