42. model/transformer — generate

Part: VI · Model IO
Package: github.com/openfluke/welvet/model/transformer
Status: ok — ✅

When

Checkpoints, HF import, tokenize, sample, or decode (model/transformer).

Where

import "github.com/openfluke/welvet/model/transformer"

cd 42-transformer && source ../env.sh && go run .

Why

ENTITY packs must run as Llama-style decoders with KV cache, profiles (SIMD/WebGPU/fused), and chat templates.

What

LoadEntity → Model; Generate; ApplyExec profiles; ExportFusedGPUSpec / hybrid sync.

Sample output (captured)

open model.entity: no such file or directory

Live capture from go run ./cmd/runall on local ../../welvet (exit 0).

Source

Copied from the Welvet feature book examples (openfluke.github.io/welvet/examples/42-transformer).

package main

import (
	"fmt"

	"github.com/openfluke/welvet/model/tokenizer"
	"github.com/openfluke/welvet/model/transformer"
)

func main() {
	m, err := transformer.LoadEntity("model.entity")
	if err != nil {
		fmt.Println(err)
		return
	}
	tok, err := tokenizer.LoadTokenizer("tokenizer.json")
	if err != nil {
		panic(err)
	}
	if err := m.ApplyExec(transformer.ProfileSIMDMultiCore()); err != nil {
		panic(err)
	}
	text, _, err := m.Generate(
		tok.Encode, tok.Decode, nil,
		"You are helpful.", "Say hi.",
		transformer.GenOptions{MaxTokens: 32, Silent: true},
	)
	fmt.Println(text, err)
}