mirror of
https://github.com/ollama/ollama.git
synced 2026-01-12 00:06:57 +08:00
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>
108 lines
2.2 KiB
Go
108 lines
2.2 KiB
Go
package model
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/google/go-cmp/cmp"
|
|
)
|
|
|
|
func TestSpecialVocabulary(t *testing.T) {
|
|
vocab := &Vocabulary{
|
|
Values: []string{"<|startoftext|>", "<|endoftext|>", "<|tool_call_start|>", "<|tool_call_end|>", "hi"},
|
|
Types: []int32{TOKEN_TYPE_CONTROL, TOKEN_TYPE_CONTROL, TOKEN_TYPE_USER_DEFINED, TOKEN_TYPE_USER_DEFINED, TOKEN_TYPE_NORMAL},
|
|
}
|
|
|
|
specialVocab := vocab.SpecialVocabulary()
|
|
|
|
if len(specialVocab) != 4 {
|
|
t.Errorf("expected 4 special tokens, got %d", len(specialVocab))
|
|
}
|
|
}
|
|
|
|
func TestAddSpecialVocabulary(t *testing.T) {
|
|
cases := []struct {
|
|
name string
|
|
vocab *Vocabulary
|
|
input []int32
|
|
want []int32
|
|
}{
|
|
{
|
|
name: "add bos",
|
|
vocab: &Vocabulary{
|
|
BOS: []int32{0},
|
|
EOS: []int32{1},
|
|
AddBOS: true,
|
|
AddEOS: false,
|
|
},
|
|
input: []int32{2, 3, 4},
|
|
want: []int32{0, 2, 3, 4},
|
|
},
|
|
{
|
|
// TODO(mxyng): this is to match previous behaviour
|
|
name: "add bos when already present",
|
|
vocab: &Vocabulary{
|
|
BOS: []int32{0},
|
|
EOS: []int32{1},
|
|
AddBOS: true,
|
|
AddEOS: false,
|
|
},
|
|
input: []int32{0, 2, 3, 4},
|
|
want: []int32{0, 0, 2, 3, 4},
|
|
},
|
|
{
|
|
name: "add eos",
|
|
vocab: &Vocabulary{
|
|
BOS: []int32{0},
|
|
EOS: []int32{1},
|
|
AddBOS: false,
|
|
AddEOS: true,
|
|
},
|
|
input: []int32{2, 3, 4},
|
|
want: []int32{2, 3, 4, 1},
|
|
},
|
|
{
|
|
// TODO(mxyng): this is to match previous behaviour
|
|
name: "add eos when already present",
|
|
vocab: &Vocabulary{
|
|
BOS: []int32{0},
|
|
EOS: []int32{1},
|
|
AddBOS: false,
|
|
AddEOS: true,
|
|
},
|
|
input: []int32{2, 3, 4, 1},
|
|
want: []int32{2, 3, 4, 1, 1},
|
|
},
|
|
{
|
|
name: "add both",
|
|
vocab: &Vocabulary{
|
|
BOS: []int32{0},
|
|
EOS: []int32{1},
|
|
AddBOS: true,
|
|
AddEOS: true,
|
|
},
|
|
input: []int32{2, 3, 4},
|
|
want: []int32{0, 2, 3, 4, 1},
|
|
},
|
|
{
|
|
name: "add bos to empty inputs",
|
|
vocab: &Vocabulary{
|
|
BOS: []int32{0},
|
|
EOS: []int32{1},
|
|
AddBOS: true,
|
|
AddEOS: false,
|
|
},
|
|
input: []int32{},
|
|
want: []int32{0},
|
|
},
|
|
}
|
|
|
|
for _, tt := range cases {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got := tt.vocab.addSpecials(tt.input)
|
|
if diff := cmp.Diff(tt.want, got); diff != "" {
|
|
t.Errorf("no match (-want +got):\n%s", diff)
|
|
}
|
|
})
|
|
}
|
|
}
|