j6-plugin-set-fake-quantize

j6-plugin-set-fake-quantize is a skill for Claude Code, Codex from HorizonRobotics/OE-Skills. It costs 54 tokens per session (833 once invoked), scanned A, original, Apache-2.0.

A coding guide for choosing the fake-quantization state of a model in Horizon's PyTorch quantization workflow. Fake quantization simulates reduced-precision calculations so a model can be prepared for quantized deployment.

In plain words
What is it for?
Adding `set_fake_quantize` before calibration, QAT training, or validation, using the matching state for each stage.
Why use it?
It prevents calibration, quantization-aware training, and validation from running with the wrong model state, without changing other model or training code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Adding set_fake_quantize before calibration, QAT training, or validation, using the matching state for each stage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horizonrobotics/oe-skills/j6-plugin-set-fake-quantize
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HorizonRobotics/OE-Skills --skill j6-plugin-set-fake-quantize
Clone the repo
git clone --depth 1 https://github.com/HorizonRobotics/OE-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for j6-plugin-set-fake-quantize

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-set-fake-quantize/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-set-fake-quantize)
Your own site
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-set-fake-quantize"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-set-fake-quantize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for j6-plugin-set-fake-quantize

Your own site · 80×15
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-set-fake-quantize"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-set-fake-quantize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 833 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00833
Opus 5.5 $0.00022 $0.00333
Sonnet 5.5 $0.00011 $0.00167
Haiku 4.5 $0.00005 $0.00083

Measured 2mo ago against content hash d0b93d749046, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

j6-plugin-set-fake-quantize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

horizon/skills/plugin/j6-plugin-adaptation/j6-plugin-set-fake-quantize/SKILL.md · 106 lines

What it actually says

为 Horizon 量化流程设置 fake quantize 状态(set_fake_quantize)

目标

在使用 horizon_plugin_pytorch 的 Calibration / QAT / Validation 流程时,按阶段为模型设置正确的 fake quantize 状态:

  • Calibration 前:CALIBRATION
  • QAT(训练)前:QAT
  • Validation(评估)前:VALIDATION

本 Skill 只做一件事:在合适位置添加/调用

horizon.quantization.set_fake_quantize(model, horizon.quantization.FakeQuantState.<STATE>)

不引入任何其他改动(不改模型结构、不改 qconfig、不改 prepare/convert、不改训练/数据逻辑)。

标准改法(通用模板)

1) 选择状态枚举值

fake quantize 有三种状态:

class FakeQuantState(Enum):
    QAT = "qat"
    CALIBRATION = "calibration"
    VALIDATION = "validation"

语义与行为约束(按官方说明):

  • CALIBRATION:仅观测各算子输入/输出统计量(observer 统计)。
  • QAT:观测统计量 + 执行伪量化(fake quant)。
  • VALIDATION:仅执行伪量化,不再观测统计量。

2) 在阶段入口处调用 set_fake_quantize

Calibration 前
model.eval()
horizon.quantization.set_fake_quantize(
    model, horizon.quantization.FakeQuantState.CALIBRATION
)
QAT(训练)前
horizon.quantization.set_fake_quantize(
    model, horizon.quantization.FakeQuantState.QAT
)
Validation(评估)前
model.eval()
horizon.quantization.set_fake_quantize(
    model, horizon.quantization.FakeQuantState.VALIDATION
)

关键注意事项(必须遵守)

1) Calibration 状态下不要再调用 model.eval()

一旦设置为 FakeQuantState.CALIBRATION,请勿再使用 model.eval(),否则将无法正常进行校准。

如果你的流程需要在校准时切换到 eval,请改为:

  • 先 model.eval()(如果你确实需要 eval)
  • 再 set_fake_quantize(..., CALIBRATION)

并确保后续不再重复调用 model.eval()。

2) Validation 的顺序要求

Validation 推荐固定顺序:

  • 先 model.eval()
  • 再 set_fake_quantize(..., VALIDATION)

以保证评估时不再更新统计量,仅执行伪量化。

3) 不要混用状态(尤其是训练/评估循环)

如果你的代码存在多个入口(如:训练脚本、校准脚本、导出脚本),每个入口都要在其对应阶段入口处显式设置状态,避免:

  • QAT 训练时仍处于 CALIBRATION
  • Validation 评估时仍处于 QAT

快速自检清单

  • Calibration 前调用:set_fake_quantize(model, CALIBRATION),且之后不再 model.eval()。
  • QAT 训练前调用:set_fake_quantize(model, QAT)。
  • Validation 前调用:model.eval() 后紧接 set_fake_quantize(model, VALIDATION)。
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 106 lines · 54 tokens per session scan A d0b93d749046

Subscribe to this mod's changes

j6-plugin-set-fake-quantize is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 833 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

j6-plugin-set-fake-quantize compared with skills from other repositories

j6-plugin-set-fake-quantize next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
j6-plugin-set-fake-quantizeHorizonRobotics/OE-SkillsSkill274mo agoApache-2.0A54Claude Code, Codex
agent-platform-model-registrygoogle/skillsSkill22kyesterdayApache-2.0A60Claude Code, Codex
foundry-config-setupmicrosoft/agent-frameworkSkill15kyesterdayMITA65Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skillsSkill22kyesterdayApache-2.0A132Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA35Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
finetuningmicrosoft/skillsSkill3.2kyesterdayMITA132Claude Code