fixes for maverick

This commit is contained in:
Michael Yang
2025-04-21 10:45:56 -07:00
committed by Michael Yang
parent 8bf11b84c1
commit 7ba9fa9c7d
3 changed files with 53 additions and 26 deletions

View File

@@ -35,7 +35,8 @@ func (p *Projector) Forward(ctx ml.Context, visionOutputs ml.Tensor) ml.Tensor {
func New(c fs.Config) (model.Model, error) {
m := Model{
BytePairEncoding: model.NewBytePairEncoding(
c.String("tokenizer.ggml.pretokenizer", `(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+`),
c.String("tokenizer.ggml.pretokenizer",
`[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}]*[\p{Ll}\p{Lm}\p{Lo}\p{M}]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?|[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}]+[\p{Ll}\p{Lm}\p{Lo}\p{M}]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n/]*|\s*[\r\n]+|\s+(?!\S)|\s+`),
&model.Vocabulary{
Values: c.Strings("tokenizer.ggml.tokens"),
Types: c.Uints("tokenizer.ggml.token_type"),
@@ -52,7 +53,7 @@ func New(c fs.Config) (model.Model, error) {
}
m.Cache = kvcache.NewWrapperCache(
kvcache.NewChunkedAttentionCache(int32(c.Uint("attention.chunk_size")), m.Shift),
kvcache.NewChunkedAttentionCache(int32(c.Uint("attention.chunk_size", 8192)), m.Shift),
kvcache.NewCausalCache(m.Shift),
)