jev-web 0.3.1 → 0.3.3

package/src/config.mjs

@@ -1,65 +1,65 @@
-// jev-web — model defaults, backend resolution, and model-side config.
-//
-// Defaults point at the reference ONNX export of com-kotobalabs/open-jev-
-// deberta-v3-large (Apache-2.0), pinned by revision for reproducibility. Any
-// repo with the same typed-decision graph layout works: pass `model` and
-// optionally `revision`.
-
-export const DEFAULT_MODEL = "onnx-community/open-jev-deberta-v3-large-ONNX";
-export const DEFAULT_REVISION = "7c79f25b5ac496089f448a969c801872ad59d31c";
-export const DEFAULT_TEMPERATURE = 1.05;
-export const DEFAULT_MARKERS = ["[STATE]", "[Q]", "[OPT]"];
-export const DEFAULT_MAX_STATE_TOKENS = 256;
-export const DEFAULT_MAX_LEN = 512;
-
-const HF_BASE = "https://huggingface.co";
-
-export function resolveDevice({ device = "auto", webgpu = false } = {}) {
-  if (device && device !== "auto") return device;
-  return webgpu ? "webgpu" : "wasm";
-}
-
-// Quantized WebGPU kernels are f16-friendly (q4f16); WASM wants the
-// non-f16 q4 build. fp32/fp16/q8 stay explicit opt-ins.
-export function resolveDtype(device, dtype = "auto") {
-  if (dtype && dtype !== "auto") return dtype;
-  return device === "webgpu" ? "q4f16" : "q4";
-}
-
-export async function detectWebGPU(scope = globalThis) {
-  try {
-    if (!scope?.navigator?.gpu?.requestAdapter) return false;
-    return !!(await scope.navigator.gpu.requestAdapter());
-  } catch {
-    return false;
-  }
-}
-
-// Read the model's own calibration/marker config when the repo ships one
-// (open_jev_config.json), else fall back to the published reference values.
-export async function loadModelConfig({ model = DEFAULT_MODEL, revision = DEFAULT_REVISION, fetchImpl = fetch } = {}) {
-  const fallback = {
-    temperature: DEFAULT_TEMPERATURE,
-    markers: [...DEFAULT_MARKERS],
-    maxStateTokens: DEFAULT_MAX_STATE_TOKENS,
-    maxLen: DEFAULT_MAX_LEN,
-    pool: "span",
-    source: "defaults",
-  };
-  const url = `${HF_BASE}/${model}/resolve/${revision ? `${revision}/` : ""}open_jev_config.json`;
-  try {
-    const res = await fetchImpl(url, { cache: "no-store" });
-    if (!res.ok) return fallback;
-    const cfg = await res.json();
-    return {
-      temperature: Number.isFinite(Number(cfg.temperature)) ? Number(cfg.temperature) : fallback.temperature,
-      markers: Array.isArray(cfg.markers) && cfg.markers.length === 3 ? cfg.markers.map(String) : fallback.markers,
-      maxStateTokens: Number.isFinite(Number(cfg.max_state_tokens)) ? Number(cfg.max_state_tokens) : fallback.maxStateTokens,
-      maxLen: Number.isFinite(Number(cfg.max_len)) ? Number(cfg.max_len) : fallback.maxLen,
-      pool: typeof cfg.pool === "string" ? cfg.pool : fallback.pool,
-      source: "model",
-    };
-  } catch {
-    return fallback;
-  }
-}
+// jev-web — model defaults, backend resolution, and model-side config.
+//
+// Defaults point at the reference ONNX export of com-kotobalabs/open-jev-
+// deberta-v3-large (Apache-2.0), pinned by revision for reproducibility. Any
+// repo with the same typed-decision graph layout works: pass `model` and
+// optionally `revision`.
+
+export const DEFAULT_MODEL = "onnx-community/open-jev-deberta-v3-large-ONNX";
+export const DEFAULT_REVISION = "7c79f25b5ac496089f448a969c801872ad59d31c";
+export const DEFAULT_TEMPERATURE = 1.05;
+export const DEFAULT_MARKERS = ["[STATE]", "[Q]", "[OPT]"];
+export const DEFAULT_MAX_STATE_TOKENS = 256;
+export const DEFAULT_MAX_LEN = 512;
+
+const HF_BASE = "https://huggingface.co";
+
+export function resolveDevice({ device = "auto", webgpu = false } = {}) {
+  if (device && device !== "auto") return device;
+  return webgpu ? "webgpu" : "wasm";
+}
+
+// Quantized WebGPU kernels are f16-friendly (q4f16); WASM wants the
+// non-f16 q4 build. fp32/fp16/q8 stay explicit opt-ins.
+export function resolveDtype(device, dtype = "auto") {
+  if (dtype && dtype !== "auto") return dtype;
+  return device === "webgpu" ? "q4f16" : "q4";
+}
+
+export async function detectWebGPU(scope = globalThis) {
+  try {
+    if (!scope?.navigator?.gpu?.requestAdapter) return false;
+    return !!(await scope.navigator.gpu.requestAdapter());
+  } catch {
+    return false;
+  }
+}
+
+// Read the model's own calibration/marker config when the repo ships one
+// (open_jev_config.json), else fall back to the published reference values.
+export async function loadModelConfig({ model = DEFAULT_MODEL, revision = DEFAULT_REVISION, fetchImpl = fetch } = {}) {
+  const fallback = {
+    temperature: DEFAULT_TEMPERATURE,
+    markers: [...DEFAULT_MARKERS],
+    maxStateTokens: DEFAULT_MAX_STATE_TOKENS,
+    maxLen: DEFAULT_MAX_LEN,
+    pool: "span",
+    source: "defaults",
+  };
+  const url = `${HF_BASE}/${model}/resolve/${revision ? `${revision}/` : ""}open_jev_config.json`;
+  try {
+    const res = await fetchImpl(url, { cache: "no-store" });
+    if (!res.ok) return fallback;
+    const cfg = await res.json();
+    return {
+      temperature: Number.isFinite(Number(cfg.temperature)) ? Number(cfg.temperature) : fallback.temperature,
+      markers: Array.isArray(cfg.markers) && cfg.markers.length === 3 ? cfg.markers.map(String) : fallback.markers,
+      maxStateTokens: Number.isFinite(Number(cfg.max_state_tokens)) ? Number(cfg.max_state_tokens) : fallback.maxStateTokens,
+      maxLen: Number.isFinite(Number(cfg.max_len)) ? Number(cfg.max_len) : fallback.maxLen,
+      pool: typeof cfg.pool === "string" ? cfg.pool : fallback.pool,
+      source: "model",
+    };
+  } catch {
+    return fallback;
+  }
+}

package/src/encode.mjs

@@ -1,83 +1,83 @@
-// jev-web — pure input builder for open-jev-shaped models.
-//
-// Layout produced (mirrors the reference export):
-//   [CLS] [STATE] state [Q] instructions [OPT] option … [SEP]
-//
-// `seg` carries a span slot per token: option tokens get their pair index,
-// question-instruction tokens get `totalPairs + question index`, everything
-// else -1. `pair_q` / `pair_opt` list the question slot and pair slot for
-// every (question, option) pair; `groups` groups pair indices per question.
-// The ONNX graph consumes these directly (see the model's export docs).
-
-export class DecisionInputTooLongError extends Error {
-  constructor(message) {
-    super(message);
-    this.name = "DecisionInputTooLongError";
-  }
-}
-
-// Runtime-independent: take pre-tokenized ids and lay out the sequence.
-export function buildDecisionInput({
-  stateIds,
-  markers, // { cls, sep, state, question, option } single token ids
-  questions, // [{ type, instructionIds: number[], optionIds: number[][] }]
-  maxStateTokens = 256,
-  maxLen = 512,
-}) {
-  if (!Array.isArray(stateIds)) throw new TypeError("stateIds must be an array of token ids");
-  if (!Array.isArray(questions) || questions.length === 0) {
-    throw new TypeError("questions must be a non-empty array of tokenized questions");
-  }
-  for (const key of ["cls", "sep", "state", "question", "option"]) {
-    if (!Number.isInteger(markers?.[key])) throw new TypeError(`markers.${key} must be a token id`);
-  }
-
-  const truncated = stateIds.length > maxStateTokens;
-  const state = truncated ? stateIds.slice(0, maxStateTokens) : stateIds;
-
-  const inputIds = [markers.cls, markers.state, ...state];
-  const seg = inputIds.map(() => -1);
-  const pairQ = [];
-  const pairOpt = [];
-  const groups = [];
-  const totalPairs = questions.reduce((n, q) => n + q.optionIds.length, 0);
-
-  questions.forEach((q, qi) => {
-    inputIds.push(markers.question, ...q.instructionIds);
-    seg.push(-1, ...q.instructionIds.map(() => totalPairs + qi));
-    groups.push(
-      q.optionIds.map((ids) => {
-        inputIds.push(markers.option, ...ids);
-        seg.push(-1, ...ids.map(() => pairOpt.length));
-        pairQ.push(totalPairs + qi);
-        pairOpt.push(pairOpt.length);
-        return pairOpt.length - 1;
-      }),
-    );
-  });
-  inputIds.push(markers.sep);
-  seg.push(-1);
-
-  if (inputIds.length > maxLen) {
-    throw new DecisionInputTooLongError(
-      `decision input is ${inputIds.length} tokens, over the ${maxLen}-token limit ` +
-        `(state capped at ${maxStateTokens}) — shorten the questions or the state`,
-    );
-  }
-  return { inputIds, seg, pairQ, pairOpt, groups, truncated, length: inputIds.length, totalPairs };
-}
-
-// Shared marker lookup: every marker must encode to exactly one token id.
-// (Custom typed-decision exports add [STATE]/[Q]/[OPT] to the tokenizer; if
-// they are missing, the model is not a typed-decision export.)
-export function typedMarkerIds(encodeFn, { markers = ["[STATE]", "[Q]", "[OPT]"], cls = "[CLS]", sep = "[SEP]" } = {}) {
-  const one = (text) => {
-    const ids = encodeFn(text);
-    if (!Array.isArray(ids) || ids.length !== 1) {
-      throw new Error(`marker ${text} must encode to exactly one token (got ${ids?.length ?? 0})`);
-    }
-    return ids[0];
-  };
-  const [state, question, option] = markers.map(one);
-  return { cls: one(cls), sep: one(sep), state, question, option };
-}
+// jev-web — pure input builder for open-jev-shaped models.
+//
+// Layout produced (mirrors the reference export):
+//   [CLS] [STATE] state [Q] instructions [OPT] option … [SEP]
+//
+// `seg` carries a span slot per token: option tokens get their pair index,
+// question-instruction tokens get `totalPairs + question index`, everything
+// else -1. `pair_q` / `pair_opt` list the question slot and pair slot for
+// every (question, option) pair; `groups` groups pair indices per question.
+// The ONNX graph consumes these directly (see the model's export docs).
+
+export class DecisionInputTooLongError extends Error {
+  constructor(message) {
+    super(message);
+    this.name = "DecisionInputTooLongError";
+  }
+}
+
+// Runtime-independent: take pre-tokenized ids and lay out the sequence.
+export function buildDecisionInput({
+  stateIds,
+  markers, // { cls, sep, state, question, option } single token ids
+  questions, // [{ type, instructionIds: number[], optionIds: number[][] }]
+  maxStateTokens = 256,
+  maxLen = 512,
+}) {
+  if (!Array.isArray(stateIds)) throw new TypeError("stateIds must be an array of token ids");
+  if (!Array.isArray(questions) || questions.length === 0) {
+    throw new TypeError("questions must be a non-empty array of tokenized questions");
+  }
+  for (const key of ["cls", "sep", "state", "question", "option"]) {
+    if (!Number.isInteger(markers?.[key])) throw new TypeError(`markers.${key} must be a token id`);
+  }
+
+  const truncated = stateIds.length > maxStateTokens;
+  const state = truncated ? stateIds.slice(0, maxStateTokens) : stateIds;
+
+  const inputIds = [markers.cls, markers.state, ...state];
+  const seg = inputIds.map(() => -1);
+  const pairQ = [];
+  const pairOpt = [];
+  const groups = [];
+  const totalPairs = questions.reduce((n, q) => n + q.optionIds.length, 0);
+
+  questions.forEach((q, qi) => {
+    inputIds.push(markers.question, ...q.instructionIds);
+    seg.push(-1, ...q.instructionIds.map(() => totalPairs + qi));
+    groups.push(
+      q.optionIds.map((ids) => {
+        inputIds.push(markers.option, ...ids);
+        seg.push(-1, ...ids.map(() => pairOpt.length));
+        pairQ.push(totalPairs + qi);
+        pairOpt.push(pairOpt.length);
+        return pairOpt.length - 1;
+      }),
+    );
+  });
+  inputIds.push(markers.sep);
+  seg.push(-1);
+
+  if (inputIds.length > maxLen) {
+    throw new DecisionInputTooLongError(
+      `decision input is ${inputIds.length} tokens, over the ${maxLen}-token limit ` +
+        `(state capped at ${maxStateTokens}) — shorten the questions or the state`,
+    );
+  }
+  return { inputIds, seg, pairQ, pairOpt, groups, truncated, length: inputIds.length, totalPairs };
+}
+
+// Shared marker lookup: every marker must encode to exactly one token id.
+// (Custom typed-decision exports add [STATE]/[Q]/[OPT] to the tokenizer; if
+// they are missing, the model is not a typed-decision export.)
+export function typedMarkerIds(encodeFn, { markers = ["[STATE]", "[Q]", "[OPT]"], cls = "[CLS]", sep = "[SEP]" } = {}) {
+  const one = (text) => {
+    const ids = encodeFn(text);
+    if (!Array.isArray(ids) || ids.length !== 1) {
+      throw new Error(`marker ${text} must encode to exactly one token (got ${ids?.length ?? 0})`);
+    }
+    return ids[0];
+  };
+  const [state, question, option] = markers.map(one);
+  return { cls: one(cls), sep: one(sep), state, question, option };
+}

package/src/index.mjs

@@ -1,42 +1,42 @@
-// jev-web — public API (typed decisions in the browser).
-export { createDecider } from "./session.mjs";
-export {
-  registerDecisionFamily, createDecisionRuntime,
-  listDecisionFamilies, getDecisionFamily,
-} from "./registry.mjs";
-export { normalizeQuestions, QUESTION_TYPES, NOUL_OPTIONS } from "./questions.mjs";
-export { buildDecisionInput, typedMarkerIds, DecisionInputTooLongError } from "./encode.mjs";
-export { answersFromScores, softmaxWithTemperature } from "./answers.mjs";
-export {
-  createLayaDecider,
-  buildLayaSequence,
-  collateLayaItems,
-  layaAnswersFromLogits,
-  layaTokenizerAdapter,
-  renderLayaOptions,
-  layaTempBucket,
-  clampTemperature,
-  LAYA_DEFAULT_MODEL,
-  LAYA_DEFAULT_REVISION,
-  LAYA_DEFAULT_SUBFOLDER,
-  LAYA_DEFAULT_TEMPERATURES,
-  LAYA_DEFAULT_TEMPERATURES_BY_OPTIONS,
-  LAYA_DEFAULT_MAX_LEN,
-  LAYA_DEFAULT_HEAD_MAX_LEN,
-  LAYA_DEFAULT_MAX_PREFIXES,
-  LAYA_QTYPE,
-  LAYA_TEMP_MIN,
-  LAYA_TEMP_MAX,
-} from "./laya.mjs";
-export {
-  DEFAULT_MODEL,
-  DEFAULT_REVISION,
-  DEFAULT_TEMPERATURE,
-  DEFAULT_MARKERS,
-  DEFAULT_MAX_STATE_TOKENS,
-  DEFAULT_MAX_LEN,
-  resolveDevice,
-  resolveDtype,
-  detectWebGPU,
-  loadModelConfig,
-} from "./config.mjs";
+// jev-web — public API (typed decisions in the browser).
+export { createDecider } from "./session.mjs";
+export {
+  registerDecisionFamily, createDecisionRuntime,
+  listDecisionFamilies, getDecisionFamily,
+} from "./registry.mjs";
+export { normalizeQuestions, QUESTION_TYPES, NOUL_OPTIONS } from "./questions.mjs";
+export { buildDecisionInput, typedMarkerIds, DecisionInputTooLongError } from "./encode.mjs";
+export { answersFromScores, softmaxWithTemperature } from "./answers.mjs";
+export {
+  createLayaDecider,
+  buildLayaSequence,
+  collateLayaItems,
+  layaAnswersFromLogits,
+  layaTokenizerAdapter,
+  renderLayaOptions,
+  layaTempBucket,
+  clampTemperature,
+  LAYA_DEFAULT_MODEL,
+  LAYA_DEFAULT_REVISION,
+  LAYA_DEFAULT_SUBFOLDER,
+  LAYA_DEFAULT_TEMPERATURES,
+  LAYA_DEFAULT_TEMPERATURES_BY_OPTIONS,
+  LAYA_DEFAULT_MAX_LEN,
+  LAYA_DEFAULT_HEAD_MAX_LEN,
+  LAYA_DEFAULT_MAX_PREFIXES,
+  LAYA_QTYPE,
+  LAYA_TEMP_MIN,
+  LAYA_TEMP_MAX,
+} from "./laya.mjs";
+export {
+  DEFAULT_MODEL,
+  DEFAULT_REVISION,
+  DEFAULT_TEMPERATURE,
+  DEFAULT_MARKERS,
+  DEFAULT_MAX_STATE_TOKENS,
+  DEFAULT_MAX_LEN,
+  resolveDevice,
+  resolveDtype,
+  detectWebGPU,
+  loadModelConfig,
+} from "./config.mjs";