Skip to content

pre-compile regexp2 with regexp2cg #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bluescreen10 merged 2 commits into from
Feb 12, 2025
Merged

pre-compile regexp2 with regexp2cg #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4587810
pre-compile regexp2 with regexp2cg
terwey Dec 4, 2024
2e19c14
Added a go generate command for the compiled regular expression
Feb 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/go.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ jobs:
- name: Set up Go
uses: actions/setup-go@v3
with:
go-version: "1.20"
go-version: "1.24"

- name: Build
run: go build -v ./...
Expand Down
5 changes: 4 additions & 1 deletion codec/cl100k_base.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,13 @@ import "github.com/dlclark/regexp2"

func NewCl100kBase() *Codec {
cl100kBaseVocabOnce.Do(cl100kBaseVocabInit)

splitRegexp := regexp2.MustCompile(`(?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+`, regexp2.None)

return &Codec{
name: "cl100k_base",
vocabulary: cl100kBaseVocab,
splitRegexp: regexp2.MustCompile(`(?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+`, regexp2.None),
splitRegexp: splitRegexp,
specialTokens: map[string]uint{
"<|endoftext|>": 100257,
"<|fim_prefix|>": 100258,
Expand Down
18 changes: 8 additions & 10 deletions codec/o200k_base.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,17 +4,15 @@ import "github.com/dlclark/regexp2"

func NewO200kBase() *Codec {
o200kBaseVocabOnce.Do(o200kBaseVocabInit)

splitRegexp := regexp2.MustCompile(
`[^\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+`,
regexp2.None)

return &Codec{
name: "o200k_base",
vocabulary: o200kBaseVocab,
splitRegexp: regexp2.MustCompile(
`[^\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+`,
regexp2.None),
name: "o200k_base",
vocabulary: o200kBaseVocab,
splitRegexp: splitRegexp,
specialTokens: map[string]uint{
"<|endoftext|>": 199999,
"<|endofprompt|>": 200018,
Expand Down
5 changes: 4 additions & 1 deletion codec/p50k_base.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,13 @@ import "github.com/dlclark/regexp2"

func NewP50kBase() *Codec {
p50kBaseVocabOnce.Do(p50kBaseVocabInit)

splitRegexp := regexp2.MustCompile(`'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+`, regexp2.None)

return &Codec{
name: "p50k_base",
vocabulary: p50kBaseVocab,
splitRegexp: regexp2.MustCompile(`'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+`, regexp2.None),
splitRegexp: splitRegexp,
specialTokens: map[string]uint{
"<|endoftext|>": 50256,
},
Expand Down
5 changes: 4 additions & 1 deletion codec/p50k_edit.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,13 @@ import "github.com/dlclark/regexp2"

func NewP50kEdit() *Codec {
p50kBaseVocabOnce.Do(p50kBaseVocabInit)

splitRegexp := regexp2.MustCompile(`'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+`, regexp2.None)

return &Codec{
name: "p50k_edit",
vocabulary: p50kBaseVocab,
splitRegexp: regexp2.MustCompile(`'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+`, regexp2.None),
splitRegexp: splitRegexp,
specialTokens: map[string]uint{
"<|endoftext|>": 50256,
"<|fim_prefix|>": 50281,
Expand Down
5 changes: 4 additions & 1 deletion codec/r50k_base.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,13 @@ import "github.com/dlclark/regexp2"

func NewR50kBase() *Codec {
r50kBaseVocabOnce.Do(r50kBaseVocabInit)

splitRegexp := regexp2.MustCompile(`'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+`, regexp2.None)

return &Codec{
name: "r50k_base",
vocabulary: r50kBaseVocab,
splitRegexp: regexp2.MustCompile(`'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+`, regexp2.None),
splitRegexp: splitRegexp,
specialTokens: map[string]uint{
"<|endoftext|>": 50256,
},
Expand Down
Loading