本文へ移動
cccskills
無料GitHub で公開

chinese-llama-alpaca-2

Routes Chinese-LLaMA-Alpaca-2 training, inference, serving, evaluation, and integration workflows.

VectorSpaceLab/AREX-Skill
インストール方法を見る

含まれるファイル（74）

  • SKILL.md2.8 KB
  • assets/prompts/alpaca-2-long.txt140 B
  • assets/prompts/alpaca-2.txt65 B
  • assets/tokenizer/special_tokens_map.json435 B
  • assets/tokenizer/tokenizer_config.json748 B
  • assets/tokenizer/tokenizer.model824.6 KB
  • references/model-overview.md2.3 KB
  • references/prompt-and-tokenizer.md1012 B
  • references/repo-provenance.md1.4 KB
  • references/repo-routing-metadata.json568 B
  • references/troubleshooting.md2.8 KB
  • references/workflows.md3.8 KB
  • sub-skills/api-serving/references/troubleshooting.md1.2 KB
  • sub-skills/api-serving/references/workflows.md2.1 KB
  • sub-skills/api-serving/scripts/attn_and_long_ctx_patches.py10.1 KB
  • sub-skills/api-serving/scripts/openai_server_demo/openai_api_protocol_vllm.py5.0 KB
  • sub-skills/api-serving/scripts/openai_server_demo/openai_api_protocol.py2.6 KB
  • sub-skills/api-serving/scripts/openai_server_demo/openai_api_server_vllm.py26.2 KB
  • sub-skills/api-serving/scripts/openai_server_demo/openai_api_server.py12.7 KB
  • sub-skills/api-serving/SKILL.md1.9 KB
  • sub-skills/evaluation/references/troubleshooting.md1.2 KB
  • sub-skills/evaluation/references/workflows.md2.1 KB
  • sub-skills/evaluation/scripts/attn_and_long_ctx_patches.py10.1 KB
  • sub-skills/evaluation/scripts/ceval/eval.py4.8 KB
  • sub-skills/evaluation/scripts/ceval/evaluator.py1.5 KB
  • sub-skills/evaluation/scripts/ceval/llama_evaluator.py9.5 KB
  • sub-skills/evaluation/scripts/ceval/subject_mapping.json5.2 KB
  • sub-skills/evaluation/scripts/cmmlu/categories.py5.9 KB
  • sub-skills/evaluation/scripts/cmmlu/eval.py5.2 KB
  • sub-skills/evaluation/scripts/cmmlu/evaluator.py1.5 KB
  • sub-skills/evaluation/scripts/cmmlu/llama2_evaluator.py9.6 KB
  • sub-skills/evaluation/scripts/longbench/config/dataset2maxlen.json459 B
  • sub-skills/evaluation/scripts/longbench/config/dataset2prompt.json5.3 KB
  • sub-skills/evaluation/scripts/longbench/eval.py3.8 KB
  • sub-skills/evaluation/scripts/longbench/metrics.py5.5 KB
  • sub-skills/evaluation/scripts/longbench/pred_llama2.py9.0 KB
  • sub-skills/evaluation/scripts/longbench/requirements.txt70 B
  • sub-skills/evaluation/SKILL.md1.9 KB
  • sub-skills/hf-inference/references/troubleshooting.md1.2 KB
  • sub-skills/hf-inference/references/workflows.md1.9 KB
  • sub-skills/hf-inference/scripts/attn_and_long_ctx_patches.py10.1 KB
  • sub-skills/hf-inference/scripts/inference/flash_attn_patch_for_inference.py3.4 KB
  • sub-skills/hf-inference/scripts/inference/gradio_demo.py24.1 KB
  • sub-skills/hf-inference/scripts/inference/inference_hf.py21.0 KB
  • sub-skills/hf-inference/scripts/inference/speculative_sample.py19.9 KB
  • sub-skills/hf-inference/SKILL.md2.3 KB
  • sub-skills/local-integrations/references/troubleshooting.md1.1 KB
  • sub-skills/local-integrations/references/workflows.md1.8 KB
  • sub-skills/local-integrations/scripts/llama-cpp/chat.sh702 B
  • sub-skills/local-integrations/scripts/llama-cpp/server_curl_example.sh706 B
  • sub-skills/local-integrations/SKILL.md1.8 KB
  • sub-skills/train-and-merge/references/troubleshooting.md1.4 KB
  • sub-skills/train-and-merge/references/workflows.md2.2 KB
  • sub-skills/train-and-merge/scripts/merge_llama2_with_chinese_lora_low_mem.py15.0 KB
  • sub-skills/train-and-merge/scripts/training/build_dataset.py3.9 KB
  • sub-skills/train-and-merge/scripts/training/ds_zero2_no_offload.json686 B
  • sub-skills/train-and-merge/scripts/training/peft/__init__.py1.6 KB
  • sub-skills/train-and-merge/scripts/training/peft/mapping.py5.5 KB
  • sub-skills/train-and-merge/scripts/training/peft/peft_model.py42.7 KB
  • sub-skills/train-and-merge/scripts/training/peft/tuners/__init__.py1.0 KB
  • sub-skills/train-and-merge/scripts/training/peft/tuners/lora.py32.6 KB
  • sub-skills/train-and-merge/scripts/training/peft/tuners/p_tuning.py6.5 KB
  • sub-skills/train-and-merge/scripts/training/peft/tuners/prefix_tuning.py3.6 KB
  • sub-skills/train-and-merge/scripts/training/peft/tuners/prompt_tuning.py4.7 KB
  • sub-skills/train-and-merge/scripts/training/peft/utils/__init__.py1.2 KB
  • sub-skills/train-and-merge/scripts/training/peft/utils/adapters_utils.py730 B
  • sub-skills/train-and-merge/scripts/training/peft/utils/config.py6.4 KB
  • sub-skills/train-and-merge/scripts/training/peft/utils/other.py3.7 KB
  • sub-skills/train-and-merge/scripts/training/peft/utils/save_and_load.py3.2 KB
  • sub-skills/train-and-merge/scripts/training/run_clm_pt_with_peft.py31.8 KB
  • sub-skills/train-and-merge/scripts/training/run_clm_sft_with_peft.py21.1 KB
  • sub-skills/train-and-merge/scripts/training/run_pt.sh1.9 KB
  • sub-skills/train-and-merge/scripts/training/run_sft.sh2.1 KB
  • sub-skills/train-and-merge/SKILL.md2.3 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Chinese-LLaMA-Alpaca-2

This skill routes work for the Chinese-LLaMA-2 and Chinese-Alpaca-2 repository. It is intentionally a router, not a full manual.

Use it when a task mentions:

  • Chinese-LLaMA-2 or Chinese-Alpaca-2 model paths, tokenizers, or prompts
  • pretraining, SFT, LoRA merging, or model conversion
  • local generation, Gradio chat, speculative sampling, or long-context helpers
  • OpenAI-compatible serving, HTTP endpoints, or deployment wrappers
  • C-Eval, CMMLU, LongBench, or benchmark result files
  • llama.cpp launch wrappers or the repo's retrieval-style integration notes

Pick a sub-skill

Task familyRead
Dataset prep, pretraining, SFT, or merge/exportsub-skills/train-and-merge/SKILL.md
Transformers inference, chat UI, speculative sampling, or prompt wrappingsub-skills/hf-inference/SKILL.md
OpenAI-style API serving or the FastAPI serversub-skills/api-serving/SKILL.md
C-Eval, CMMLU, or LongBench evaluationsub-skills/evaluation/SKILL.md
llama.cpp wrappers or external integration notessub-skills/local-integrations/SKILL.md

Bundled assets

  • assets/prompts/alpaca-2.txt
  • assets/prompts/alpaca-2-long.txt
  • assets/tokenizer/

Read references/prompt-and-tokenizer.md before changing prompt text or tokenizer assumptions.

Cross-cutting references

  • references/workflows.md for the repository's main workflow map
  • references/model-overview.md for model family, context, and backend compatibility guidance
  • references/troubleshooting.md for shared failure modes
  • references/repo-provenance.md for source commit and staleness checks
  • references/repo-routing-metadata.json for router import metadata

Router behavior

  • Prefer the most specific sub-skill.
  • Use the training sub-skill for data preparation or merge/export questions even when the task also mentions inference.
  • Use the inference sub-skill for local generation or chat UX questions even when the task mentions prompt templates.
  • Use the API-serving sub-skill for OpenAI-compatible HTTP responses, request schemas, or deployment flags.
  • Use the evaluation sub-skill for benchmark configuration and result files, not for general model comparison prose.
  • Use the local-integrations sub-skill for llama.cpp wrappers and the external integration notes around retrieval-style examples.

Notes

  • The generated runtime skill is self-contained; do not rely on the source checkout staying available.
  • If a task needs more detail than this router provides, open the nearest references/*.md file instead of widening the router itself.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

3d-resnets-pytorch

無料

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

日本語の概要は準備中です。原文の説明を表示しています。

VectorSpaceLab/AREX-Skill3322026年9月3日 更新

3ddfa

無料

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

日本語の概要は準備中です。原文の説明を表示しています。

VectorSpaceLab/AREX-Skill3322026年9月3日 更新

3ddfa-v2

無料

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

日本語の概要は準備中です。原文の説明を表示しています。

VectorSpaceLab/AREX-Skill3322026年9月3日 更新

ab3dmot

無料

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

日本語の概要は準備中です。原文の説明を表示しています。

VectorSpaceLab/AREX-Skill3322026年9月3日 更新

accelerate

無料

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.

日本語の概要は準備中です。原文の説明を表示しています。

VectorSpaceLab/AREX-Skill3322026年9月3日 更新

acme

無料

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

日本語の概要は準備中です。原文の説明を表示しています。

VectorSpaceLab/AREX-Skill3322026年9月3日 更新

VectorSpaceLab のスキルをすべて見る

このスキルの問題を報告する