# bert / encoder / self

> General SOP for common requests related to bert, encoder, self.

- Skill: `ecnu-icalk/bert-encoder-self` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ecnu-icalk/bert-encoder-self`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ecnu-icalk/bert-encoder-self/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: ECNU-ICALK (https://skillmd.com/u/ecnu-icalk)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/ecnu-icalk/bert-encoder-self

---


# bert / encoder / self

General SOP for common requests related to bert, encoder, self.

## Prompt

Follow this SOP (replace specifics with placeholders like <PROJECT>/<ENV>/<VERSION>):
1) 02245dbd5831469fc8d2e8eaef1206d3.json#conv_1
2) Use the user questions below as the PRIMARY extraction evidence
3) Use the full conversation below as SECONDARY context reference
4) In the full conversation section, assistant/model replies are reference-only and not skill evidence
5) Primary User Questions (main evidence
6) generate code for question geneartion task for arabic language using arabert transformer our dataset has question and context as df and use blue score
7) i get this alueError: Unrecognized configuration class <class 'transformers.models.bert.configuration_bert.BertConfig'> for this kind of AutoModel: AutoModelForSeq2SeqLM
8) Model type should be one of BartConfig, BigBirdPegasusConfig, BlenderbotConfig, BlenderbotSmallConfig, EncoderDecoderConfig, FSMTConfig, GPTSanJapaneseConfig, LEDConfig, LongT5Config, M2M100Config, MarianConfig, MBartConfig, MT5Config, MvpConfig, NllbMoeConfig, PegasusConfig, PegasusXConfig, PLBartConfig, ProphetNetConfig, SeamlessM4TConfig, SeamlessM4Tv2Config, SwitchTransformersConfig, T5Config, UMT5Config, XLMProphetNetConfig. when use this aubmindlab/bert-base-arabert
9) i want ti user arabert not t5 when tokenize and train model
10) KeyError: "Column train not in the dataset. Current columns in the dataset: ['query', 'positive', 'input_ids', 'token_type_ids', 'attention_mask', 'labels

For each step, include: action, checks, and failure rollback/fallback plan.
Output format: for each step number, provide status/result and what to do next.

## Triggers

- Use when the user asks for a process or checklist.
- Use when you want to reuse a previously mentioned method/SOP.

## Examples

### Example 1

Input:

  Break this into best-practice, executable steps.