Songkai/kai-skill-lora

kai-skill LoRA adapters

Two LoRA adapters fine-tuned on Qwen/Qwen3-4B-Instruct-2507 for two content generation Skills: slide-creator (slide decks) and kai-report-creator (structured reports). They generate each Skill's intermediate representation (IR / BRIEF) from a task prompt, which the Skill's own deterministic renderer then turns into the final artifact.

Contents

• content/ — content adapter (4090-qlora-full-v4fix3): writes the IR for both Skills.
• router/ — router adapter (4090-router-lora-fix1): routes a request to the right Skill (including rejecting out-of-scope requests).

These are LoRA adapters, not a full model — load them on top of the base model. Each subfolder contains adapter_model.safetensors, adapter_config.json, and the base model's tokenizer files.

Evaluation (gate-3, held-out secret set, 60 cases)

Evaluation calibre: kai-report-creator v1.28.1, slide-creator v2.34.2. The held-out set was never used in training.

• Routing: 60/60
• IR first-pass validation: 46/52 (88.5%), against the pre-set ≥45/52 release gate
  • slide: 26/26 (24/26 under the stricter production pre-write calibre)
  • report: 20/26

Small model vs. large model (measured 2026-11-01)

Same 60-case held-out set, same validators, three configurations. The large model is GLM-5.3 — the teacher that generated this model's training data (BigModel coding endpoint, temperature 0.3, reasoning effort low).

	This model (Qwen3-4B + LoRA)	GLM-5.3, bare prompts	GLM-5.3, full Skill run
Routing	60/60	0/60	60/60
IR first-pass	46/52 (88.5%)	0/52	45/52 (86.5%)
IR after repair	— (one-shot)	—	52/52
Slide strict tier	24/26	—	26/26

• Bare prompts: GLM-5.3 received exactly this model's evaluation inputs, with no format specification. It answered the requests directly (final HTML) and never entered the routing/IR contract: 0/60 and 0/52. The contract is not emergent — it has to be supplied in the prompt or trained into the model.
• Full Skill run: GLM-5.3 received the complete Skill contract in context (routing rules, the IR format specification, the BRIEF template / report example — its own training-data production prompts) and up to 2 rounds of validator-feedback repair. Its first-pass quality is on par with the fine-tuned 4B (45 vs 46 of 52; per skill — slide 24/26 vs 26/26, report 21/26 vs 20/26). It pulls ahead only through the repair loop: all 7 first-pass failures were fixed in a single repair round, reaching 52/52.
• Cost: the full GLM-5.3 run used a median of 15.7 s of API time and ~3.0k tokens per triggered case (157,153 tokens for the whole set). This model generates ~1.5k output tokens per triggered case locally (≈29 routing + ≈1.5k IR; estimated by tokenizing its trained output distribution with this model's tokenizer), at a measured median of 77.7 s of local generation per triggered case on the evaluation RTX 4090 (routing 2.1 s + IR 75.6 s, 4-bit, single-stream) — not faster than the API, but with no per-call cost, no quota and no network dependency.

Known limitations

Accepted with the release decision (2026-11-01); no further fix round was run.

• report-05 / 09 / 17: stubborn kpi-semantics failures (kpi written as prose, no real number) — survived two rounds of targeted repair data.
• report-18 / 26: chart syntax — illegal chart type=table.
• report-24: chart syntax — bar block missing a required marker.
• slide-01 / 09: pass ordinary validation but are rejected by the stricter production pre-write gate; a production-gate issue, not a model failure on the ordinary calibre.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")

# Content generation
model = PeftModel.from_pretrained(base, "Songkai/kai-skill-lora", subfolder="content")
# Routing: subfolder="router"

License

Apache-2.0, following the Qwen3 base model.

---

中文说明

在 Qwen/Qwen3-4B-Instruct-2507 上微调的两个 LoRA 适配器，服务于两个内容 生成 Skill：slide-creator（幻灯片）和 kai-report-creator（结构化报告）。 模型根据任务提示生成各 Skill 的中间表示（IR / BRIEF），再由 Skill 自带的 确定性渲染器生成最终成品。

内容

• content/ —— 内容适配器（4090-qlora-full-v4fix3）：为两个 Skill 撰写 IR。
• router/ —— 路由适配器（4090-router-lora-fix1）：把请求路由到正确的 Skill（含拒绝超出范围的请求）。

这是 LoRA 适配器，不是完整模型，需要加载到基座模型上使用。每个子目录包含 adapter_model.safetensors、adapter_config.json 和基座模型的 tokenizer 文件。

评测（gate-3，60 例保密集）

评测口径：kai-report-creator v1.28.1、slide-creator v2.34.2。保密集从未用于训练。

• 路由：60/60
• IR 一次通过：46/52（88.5%），发布门槛为 ≥45/52
  • slide：26/26（生产严格口径 24/26）
  • report：20/26

与大模型的对比（2026-11-01 实测）

同一 60 例保密集、同一校验器，三种配置。大模型为 GLM-5.3（即生成本模型 训练数据的教师；BigModel coding 端点，temperature 0.3，reasoning effort low）。

	本模型（Qwen3-4B + LoRA）	GLM-5.3 裸提示	GLM-5.3 完整跑
路由	60/60	0/60	60/60
IR 一次通过	46/52（88.5%）	0/52	45/52（86.5%）
返修后通过	—（一次直出）	—	52/52
slide 严格口径	24/26	—	26/26

• 裸提示：GLM-5.3 拿到与本模型评测完全相同的输入、不给任何格式说明。 它把请求当普通需求直接作答（产最终 HTML），根本没进入路由/IR 契约： 0/60、0/52。契约不会凭空出现——要么写进提示，要么训进模型。
• 完整跑：GLM-5.3 在上下文中拿到全套 Skill 契约（路由规则、IR 格式 规范、BRIEF 模板/报告示例，即其产训练数据时的生产提示词），并可按校验器 报错返修最多 2 轮。其一次通过质量与微调后的 4B 基本打平（45 对 46； 分技能：slide 24/26 对 26/26，report 21/26 对 20/26）。它只靠返修环节 胜出：首轮失败的 7 例各返修 1 轮即全部修好，达到 52/52。
• 成本：GLM-5.3 完整跑每触发例中位 15.7 秒 API 时间、约 3.0k tokens （全集 157,153 tokens）。本模型每触发例本地生成约 1.5k 输出 tokens （路由 ≈29 + IR ≈1.5k；以本模型 tokenizer 对其训练输出分布估算）， 在评测机 RTX 4090 本地生成中位 77.7 秒/例（路由 2.1 秒 + IR 75.6 秒， 4-bit、单流，实测）——单例速度不占优，但没有 API 费用、额度和网络依赖。

已知限制

以下问题随 2026-11-01 的发布决定一并接受，不再追加修复轮次。

• report-05 / 09 / 17：kpi 语义顽固失败（kpi 写成文字、没有真实数值）， 两轮定向修复数据未能解决。
• report-18 / 26：chart 语法问题，chart type=table 不合法。
• report-24：chart 语法问题，bar 块缺少必备标记。
• slide-01 / 09：普通校验通过，但被更严格的生产预写门拒绝；属生产侧问题， 不是模型在普通口径下的失败。

使用方式

见上方 Usage 代码示例（内容生成用 subfolder="content"，路由用 subfolder="router"）。

许可证

Apache-2.0，随 Qwen3 基座模型。