mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-24 16:54:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

docs(skills): update pages, catalogs, sidebar for skill dir renames

Browse source 
Auto-gen page slugs, catalog rows/paths, sidebar entries, and zh-Hans
mirrors follow the directory renames. Also updates the install path
official/creative/audiocraft -> official/creative/audiocraft-audio-generation
in the songwriting-and-ai-music pointer section.
This commit is contained in:
teknium1 2026-07-23 20:19:42 -07:00 • committed by Teknium
parent 503da4e308
commit a98fed2470
18 changed files with 54 additions and 54 deletions
Download patch file Download diff file Expand all files Collapse all files

2
skills/creative/songwriting-and-ai-music/SKILL.md
View file

@ -298,7 +298,7 @@ cover this (heavy dependencies, so not installed by default):
`hermes skills install official/creative/heartmula`
- **audiocraft** — Meta's MusicGen (instrumental text-to-music) and
AudioGen (sound effects):
`hermes skills install official/creative/audiocraft`
`hermes skills install official/creative/audiocraft-audio-generation`
The lyric-writing and prompting craft in this skill applies to
heartmula too — its input format is lyrics with bracketed structure

4
website/docs/reference/optional-skills-catalog.md
View file

@ -55,7 +55,7 @@ hermes skills uninstall <skill-name>
| Skill | Description |
|-------|-------------|
| [**audiocraft-audio-generation**](/docs/user-guide/skills/optional/creative/creative-audiocraft) | AudioCraft: MusicGen text-to-music, AudioGen text-to-sound. |
| [**audiocraft-audio-generation**](/docs/user-guide/skills/optional/creative/creative-audiocraft-audio-generation) | AudioCraft: MusicGen text-to-music, AudioGen text-to-sound. |
| [**baoyu-article-illustrator**](/docs/user-guide/skills/optional/creative/creative-baoyu-article-illustrator) | Article illustrations: type × style × palette consistency. |
| [**baoyu-comic**](/docs/user-guide/skills/optional/creative/creative-baoyu-comic) | Knowledge comics (知识漫画): educational, biography, tutorial. |
| [**blender-mcp**](/docs/user-guide/skills/optional/creative/creative-blender-mcp) | Drive Blender via the catalog blender MCP, with bpy recipes. |
@ -164,7 +164,7 @@ hermes skills uninstall <skill-name>
| [**pytorch-lightning**](/docs/user-guide/skills/optional/mlops/mlops-pytorch-lightning) | Clean training loops with built-in distributed support. |
| [**qdrant-vector-search**](/docs/user-guide/skills/optional/mlops/mlops-qdrant) | Vector search engine for production RAG systems. |
| [**sparse-autoencoder-training**](/docs/user-guide/skills/optional/mlops/mlops-saelens) | Train sparse autoencoders to interpret model features. |
| [**segment-anything-model**](/docs/user-guide/skills/optional/mlops/mlops-models-segment-anything) | SAM: zero-shot image segmentation via points, boxes, masks. |
| [**segment-anything-model**](/docs/user-guide/skills/optional/mlops/mlops-models-segment-anything-model) | SAM: zero-shot image segmentation via points, boxes, masks. |
| [**simpo-training**](/docs/user-guide/skills/optional/mlops/mlops-simpo) | Reference-free preference alignment, simpler than DPO. |
| [**slime-rl-training**](/docs/user-guide/skills/optional/mlops/mlops-slime) | RL post-training for LLMs with Megatron and SGLang. |
| [**stable-diffusion-image-generation**](/docs/user-guide/skills/optional/mlops/mlops-stable-diffusion) | Text-to-image generation, inpainting, and img2img. |

4
website/docs/reference/skills-catalog.md
View file

@ -83,8 +83,8 @@ If a skill is missing from this list but present in the repo, the catalog is reg
|-------|-------------|------|
| [`huggingface-hub`](/docs/user-guide/skills/bundled/mlops/mlops-huggingface-hub) | HuggingFace hf CLI: search/download/upload models, datasets. | `mlops/huggingface-hub` |
| [`llama-cpp`](/docs/user-guide/skills/bundled/mlops/mlops-inference-llama-cpp) | llama.cpp local GGUF inference + HF Hub model discovery. | `mlops/inference/llama-cpp` |
| [`evaluating-llms-harness`](/docs/user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness) | lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.). | `mlops/evaluation/lm-evaluation-harness` |
| [`serving-llms-vllm`](/docs/user-guide/skills/bundled/mlops/mlops-inference-vllm) | vLLM: high-throughput LLM serving, OpenAI API, quantization. | `mlops/inference/vllm` |
| [`evaluating-llms-harness`](/docs/user-guide/skills/bundled/mlops/mlops-evaluation-evaluating-llms-harness) | lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.). | `mlops/evaluation/evaluating-llms-harness` |
| [`serving-llms-vllm`](/docs/user-guide/skills/bundled/mlops/mlops-inference-serving-llms-vllm) | vLLM: high-throughput LLM serving, OpenAI API, quantization. | `mlops/inference/serving-llms-vllm` |
| [`weights-and-biases`](/docs/user-guide/skills/bundled/mlops/mlops-evaluation-weights-and-biases) | W&B: log ML experiments, sweeps, model registry, dashboards. | `mlops/evaluation/weights-and-biases` |
## note-taking

2
website/docs/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music.md
View file

@ -309,7 +309,7 @@ cover this (heavy dependencies, so not installed by default):
`hermes skills install official/creative/heartmula`
- **audiocraft** — Meta's MusicGen (instrumental text-to-music) and
AudioGen (sound effects):
`hermes skills install official/creative/audiocraft`
`hermes skills install official/creative/audiocraft-audio-generation`
The lyric-writing and prompting craft in this skill applies to
heartmula too — its input format is lyrics with bracketed structure

10
website/docs/user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness.md → website/docs/user-guide/skills/bundled/mlops/mlops-evaluation-evaluating-llms-harness.md
View file

@ -15,7 +15,7 @@ lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
| | |
|---|---|
| Source | Bundled (installed by default) |
| Path | `skills/mlops/evaluation/lm-evaluation-harness` |
| Path | `skills/mlops/evaluation/evaluating-llms-harness` |
| Version | `1.0.0` |
| Author | Orchestra Research |
| License | MIT |
@ -483,13 +483,13 @@ lm_eval --model hf \
## Advanced topics
**Benchmark descriptions**: See [references/benchmark-guide.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/benchmark-guide.md) for detailed description of all 60+ tasks, what they measure, and interpretation.
**Benchmark descriptions**: See [references/benchmark-guide.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/benchmark-guide.md) for detailed description of all 60+ tasks, what they measure, and interpretation.
**Custom tasks**: See [references/custom-tasks.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/custom-tasks.md) for creating domain-specific evaluation tasks.
**Custom tasks**: See [references/custom-tasks.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/custom-tasks.md) for creating domain-specific evaluation tasks.
**API evaluation**: See [references/api-evaluation.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/api-evaluation.md) for evaluating OpenAI, Anthropic, and other API models.
**API evaluation**: See [references/api-evaluation.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/api-evaluation.md) for evaluating OpenAI, Anthropic, and other API models.
**Multi-GPU strategies**: See [references/distributed-eval.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/distributed-eval.md) for data parallel and tensor parallel evaluation.
**Multi-GPU strategies**: See [references/distributed-eval.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/distributed-eval.md) for data parallel and tensor parallel evaluation.
## Hardware requirements

10
website/docs/user-guide/skills/bundled/mlops/mlops-inference-vllm.md → website/docs/user-guide/skills/bundled/mlops/mlops-inference-serving-llms-vllm.md
View file

@ -15,7 +15,7 @@ vLLM: high-throughput LLM serving, OpenAI API, quantization.
| | |
|---|---|
| Source | Bundled (installed by default) |
| Path | `skills/mlops/inference/vllm` |
| Path | `skills/mlops/inference/serving-llms-vllm` |
| Version | `1.0.0` |
| Author | Orchestra Research |
| License | MIT |
@ -362,13 +362,13 @@ vllm serve MODEL --speculative-model DRAFT_MODEL
## Advanced topics
**Server deployment patterns**: See [references/server-deployment.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/server-deployment.md) for Docker, Kubernetes, and load balancing configurations.
**Server deployment patterns**: See [references/server-deployment.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/server-deployment.md) for Docker, Kubernetes, and load balancing configurations.
**Performance optimization**: See [references/optimization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/optimization.md) for PagedAttention tuning, continuous batching details, and benchmark results.
**Performance optimization**: See [references/optimization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/optimization.md) for PagedAttention tuning, continuous batching details, and benchmark results.
**Quantization guide**: See [references/quantization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/quantization.md) for AWQ/GPTQ/FP8 setup, model preparation, and accuracy comparisons.
**Quantization guide**: See [references/quantization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/quantization.md) for AWQ/GPTQ/FP8 setup, model preparation, and accuracy comparisons.
**Troubleshooting**: See [references/troubleshooting.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/troubleshooting.md) for detailed error messages, debugging steps, and performance diagnostics.
**Troubleshooting**: See [references/troubleshooting.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/troubleshooting.md) for detailed error messages, debugging steps, and performance diagnostics.
## Hardware requirements

8
website/docs/user-guide/skills/optional/creative/creative-audiocraft.md → website/docs/user-guide/skills/optional/creative/creative-audiocraft-audio-generation.md
View file

@ -14,8 +14,8 @@ AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
| | |
|---|---|
| Source | Optional — install with `hermes skills install official/creative/audiocraft` |
| Path | `optional-skills/creative/audiocraft` |
| Source | Optional — install with `hermes skills install official/creative/audiocraft-audio-generation` |
| Path | `optional-skills/creative/audiocraft-audio-generation` |
| Version | `1.0.0` |
| Author | Orchestra Research |
| License | MIT |
@ -576,8 +576,8 @@ for desc in descriptions:
## References
- **[Advanced Usage](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/creative/audiocraft/references/advanced-usage.md)** - Training, fine-tuning, deployment
- **[Troubleshooting](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/creative/audiocraft/references/troubleshooting.md)** - Common issues and solutions
- **[Advanced Usage](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/creative/audiocraft-audio-generation/references/advanced-usage.md)** - Training, fine-tuning, deployment
- **[Troubleshooting](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/creative/audiocraft-audio-generation/references/troubleshooting.md)** - Common issues and solutions
## Resources

2
website/docs/user-guide/skills/optional/creative/creative-heartmula.md
View file

@ -19,7 +19,7 @@ HeartMuLa: Suno-like song generation from lyrics + tags.
| Version | `1.0.0` |
| Platforms | linux, macos, windows |
| Tags | `music`, `audio`, `generation`, `ai`, `heartmula`, `heartcodec`, `lyrics`, `songs` |
| Related skills | [`audiocraft-audio-generation`](/docs/user-guide/skills/optional/creative/creative-audiocraft), [`songwriting-and-ai-music`](/docs/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
| Related skills | [`audiocraft-audio-generation`](/docs/user-guide/skills/optional/creative/creative-audiocraft-audio-generation), [`songwriting-and-ai-music`](/docs/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
## Reference: full SKILL.md

12
website/docs/user-guide/skills/optional/mlops/mlops-models-segment-anything.md → website/docs/user-guide/skills/optional/mlops/mlops-models-segment-anything-model.md
View file

@ -14,8 +14,8 @@ SAM: zero-shot image segmentation via points, boxes, masks.
| | |
|---|---|
| Source | Optional — install with `hermes skills install official/mlops/segment-anything` |
| Path | `optional-skills/mlops/models/segment-anything` |
| Source | Optional — install with `hermes skills install official/mlops/segment-anything-model` |
| Path | `optional-skills/mlops/models/segment-anything-model` |
| Version | `1.0.0` |
| Author | Orchestra Research |
| License | MIT |
@ -92,7 +92,7 @@ import numpy as np
from segment_anything import sam_model_registry, SamPredictor
# Load model
sam = sam_model_registry["vit_h"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/checkpoint="sam_vit_h_4b8939.pth")
sam = sam_model_registry["vit_h"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/checkpoint="sam_vit_h_4b8939.pth")
sam.to(device="cuda")
# Create predictor
@ -478,7 +478,7 @@ decoded_mask = mask_utils.decode(rle)
```python
# Use smaller model for limited VRAM
sam = sam_model_registry["vit_b"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/checkpoint="sam_vit_b_01ec64.pth")
sam = sam_model_registry["vit_b"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/checkpoint="sam_vit_b_01ec64.pth")
# Process images in batches
# Clear CUDA cache between large batches
@ -513,8 +513,8 @@ mask_generator = SamAutomaticMaskGenerator(
## References
- **[Advanced Usage](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/references/advanced-usage.md)** - Batching, fine-tuning, integration
- **[Troubleshooting](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/references/troubleshooting.md)** - Common issues and solutions
- **[Advanced Usage](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/references/advanced-usage.md)** - Batching, fine-tuning, integration
- **[Troubleshooting](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/references/troubleshooting.md)** - Common issues and solutions
## Resources

4
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/reference/optional-skills-catalog.md
View file

@ -52,7 +52,7 @@ hermes skills uninstall <skill-name>
| 技能 | 描述 |
|-------|-------------|
| [**audiocraft-audio-generation**](/user-guide/skills/optional/creative/creative-audiocraft) | AudioCraft：MusicGen 文本转音乐、AudioGen 文本转音效。 |
| [**audiocraft-audio-generation**](/user-guide/skills/optional/creative/creative-audiocraft-audio-generation) | AudioCraft：MusicGen 文本转音乐、AudioGen 文本转音效。 |
| [**blender-mcp**](/user-guide/skills/optional/creative/creative-blender-mcp) | 通过 socket 连接 blender-mcp 插件，直接从 Hermes 控制 Blender。创建 3D 对象、材质、动画，并运行任意 Blender Python（bpy）代码。适用于用户希望在 Blender 中创建或修改任何内容的场景。 |
| [**concept-diagrams**](/user-guide/skills/optional/creative/creative-concept-diagrams) | 生成扁平、极简、支持亮色/暗色模式的 SVG 图表，输出为独立 HTML 文件，采用统一的教育视觉语言，包含 9 种语义色阶、句首大写排版及自动暗色模式。最适合教育和说明类内容。 |
| [**heartmula**](/user-guide/skills/optional/creative/creative-heartmula) | HeartMuLa：根据歌词 + 标签生成类 Suno 风格的歌曲。 |
@ -144,7 +144,7 @@ hermes skills uninstall <skill-name>
| [**pytorch-lightning**](/user-guide/skills/optional/mlops/mlops-pytorch-lightning) | 高层 PyTorch 框架，提供 Trainer 类、自动分布式训练（DDP/FSDP/DeepSpeed）、回调系统及极少样板代码。同一套代码可从笔记本扩展至超算。适用于希望训练循环简洁、同时保留完整 PyTorch 灵活性的场景。 |
| [**qdrant-vector-search**](/user-guide/skills/optional/mlops/mlops-qdrant) | 高性能向量相似性搜索引擎，适用于 RAG 和语义搜索。适用于构建需要快速近邻搜索、带过滤的混合搜索或基于 Rust 高性能的可扩展向量存储的生产 RAG 系统。 |
| [**sparse-autoencoder-training**](/user-guide/skills/optional/mlops/mlops-saelens) | 提供使用 SAELens 训练和分析稀疏自编码器（SAE）的指导，将神经网络激活分解为可解释特征。适用于发现可解释特征、分析叠加现象或研究神经网络内部结构的场景。 |
| [**segment-anything-model**](/user-guide/skills/optional/mlops/mlops-models-segment-anything) | SAM：通过点、框、掩码进行零样本图像分割。 |
| [**segment-anything-model**](/user-guide/skills/optional/mlops/mlops-models-segment-anything-model) | SAM：通过点、框、掩码进行零样本图像分割。 |
| [**simpo-training**](/user-guide/skills/optional/mlops/mlops-simpo) | 用于 LLM 对齐的简单偏好优化（SimPO）。无需参考模型的 DPO 替代方案，性能更优（在 AlpacaEval 2.0 上提升 +6.4 分）。比 DPO 更高效。适用于希望简化偏好对齐流程的场景。 |
| [**slime-rl-training**](/user-guide/skills/optional/mlops/mlops-slime) | 提供使用 slime（Megatron+SGLang 框架）进行 LLM RL 后训练的指导。适用于训练 GLM 模型、实现自定义数据生成工作流或需要紧密 Megatron-LM 集成以进行 RL 扩展的场景。 |
| [**stable-diffusion-image-generation**](/user-guide/skills/optional/mlops/mlops-stable-diffusion) | 通过 HuggingFace Diffusers 使用 Stable Diffusion 模型进行最先进的文本到图像生成。适用于从文本 prompt 生成图像、图像到图像转换、图像修复或构建自定义扩散流水线的场景。 |

4
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/reference/skills-catalog.md
View file

@ -99,8 +99,8 @@ Hermes 在执行 `hermes update` 时也会同步内置技能，但同步清单
|-------|-------------|------|
| [`huggingface-hub`](/user-guide/skills/bundled/mlops/mlops-huggingface-hub) | HuggingFace hf CLI：搜索/下载/上传模型、数据集。 | `mlops/huggingface-hub` |
| [`llama-cpp`](/user-guide/skills/bundled/mlops/mlops-inference-llama-cpp) | llama.cpp 本地 GGUF 推理 + HF Hub 模型发现。 | `mlops/inference/llama-cpp` |
| [`evaluating-llms-harness`](/user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness) | lm-eval-harness：对 LLM 进行基准测试（MMLU、GSM8K 等）。 | `mlops/evaluation/lm-evaluation-harness` |
| [`serving-llms-vllm`](/user-guide/skills/bundled/mlops/mlops-inference-vllm) | vLLM：高吞吐量 LLM 服务、OpenAI API 兼容、量化支持。 | `mlops/inference/vllm` |
| [`evaluating-llms-harness`](/user-guide/skills/bundled/mlops/mlops-evaluation-evaluating-llms-harness) | lm-eval-harness：对 LLM 进行基准测试（MMLU、GSM8K 等）。 | `mlops/evaluation/evaluating-llms-harness` |
| [`serving-llms-vllm`](/user-guide/skills/bundled/mlops/mlops-inference-serving-llms-vllm) | vLLM：高吞吐量 LLM 服务、OpenAI API 兼容、量化支持。 | `mlops/inference/serving-llms-vllm` |
| [`weights-and-biases`](/user-guide/skills/bundled/mlops/mlops-evaluation-weights-and-biases) | W&B：记录 ML 实验、超参数搜索、模型注册表、仪表盘。 | `mlops/evaluation/weights-and-biases` |
## note-taking

2
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music.md
View file

@ -299,7 +299,7 @@ AI 歌手不是在阅读——它们是在发音。帮助它们：
`hermes skills install official/creative/heartmula`
- **audiocraft** — Meta 的 MusicGen（文本转纯音乐）和
AudioGen（音效生成）：
`hermes skills install official/creative/audiocraft`
`hermes skills install official/creative/audiocraft-audio-generation`
本 skill 中的歌词写作与提示词技巧同样适用于 heartmula —
它的输入格式是带方括号结构标签的歌词，加上逗号分隔的风格标签。

10
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness.md → website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/bundled/mlops/mlops-evaluation-evaluating-llms-harness.md
View file

@ -15,7 +15,7 @@ lm-eval-harness：对 LLM 进行基准测试（MMLU、GSM8K 等）。
| | |
|---|---|
| 来源 | 内置（默认安装） |
| 路径 | `skills/mlops/evaluation/lm-evaluation-harness` |
| 路径 | `skills/mlops/evaluation/evaluating-llms-harness` |
| 版本 | `1.0.0` |
| 作者 | Orchestra Research |
| 许可证 | MIT |
@ -483,13 +483,13 @@ lm_eval --model hf \
## 进阶主题
**基准描述**：参见 [references/benchmark-guide.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/benchmark-guide.md)，了解所有 60+ 个任务的详细说明、测量内容及结果解读。
**基准描述**：参见 [references/benchmark-guide.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/benchmark-guide.md)，了解所有 60+ 个任务的详细说明、测量内容及结果解读。
**自定义任务**：参见 [references/custom-tasks.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/custom-tasks.md)，了解如何创建特定领域的评估任务。
**自定义任务**：参见 [references/custom-tasks.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/custom-tasks.md)，了解如何创建特定领域的评估任务。
**API 评估**：参见 [references/api-evaluation.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/api-evaluation.md)，了解如何评估 OpenAI、Anthropic 及其他 API 模型。
**API 评估**：参见 [references/api-evaluation.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/api-evaluation.md)，了解如何评估 OpenAI、Anthropic 及其他 API 模型。
**多 GPU 策略**：参见 [references/distributed-eval.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/lm-evaluation-harness/references/distributed-eval.md)，了解数据并行与张量并行评估方案。
**多 GPU 策略**：参见 [references/distributed-eval.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/evaluation/evaluating-llms-harness/references/distributed-eval.md)，了解数据并行与张量并行评估方案。
## 硬件要求

10
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/bundled/mlops/mlops-inference-vllm.md → website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/bundled/mlops/mlops-inference-serving-llms-vllm.md
View file

@ -15,7 +15,7 @@ vLLM：高吞吐量 LLM 服务、OpenAI API、量化。
| | |
|---|---|
| 来源 | 内置（默认安装） |
| 路径 | `skills/mlops/inference/vllm` |
| 路径 | `skills/mlops/inference/serving-llms-vllm` |
| 版本 | `1.0.0` |
| 作者 | Orchestra Research |
| 许可证 | MIT |
@ -362,13 +362,13 @@ vllm serve MODEL --speculative-model DRAFT_MODEL
## 高级主题
**服务器部署模式**：参见 [references/server-deployment.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/server-deployment.md)，了解 Docker、Kubernetes 和负载均衡配置。
**服务器部署模式**：参见 [references/server-deployment.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/server-deployment.md)，了解 Docker、Kubernetes 和负载均衡配置。
**性能优化**：参见 [references/optimization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/optimization.md)，了解 PagedAttention 调优、continuous batching 详情及基准测试结果。
**性能优化**：参见 [references/optimization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/optimization.md)，了解 PagedAttention 调优、continuous batching 详情及基准测试结果。
**量化指南**：参见 [references/quantization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/quantization.md)，了解 AWQ/GPTQ/FP8 配置、模型准备及精度对比。
**量化指南**：参见 [references/quantization.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/quantization.md)，了解 AWQ/GPTQ/FP8 配置、模型准备及精度对比。
**故障排查**：参见 [references/troubleshooting.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/vllm/references/troubleshooting.md)，了解详细错误信息、调试步骤及性能诊断。
**故障排查**：参见 [references/troubleshooting.md](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/inference/serving-llms-vllm/references/troubleshooting.md)，了解详细错误信息、调试步骤及性能诊断。
## 硬件要求

4
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/optional/creative/creative-audiocraft.md → website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/optional/creative/creative-audiocraft-audio-generation.md
View file

@ -14,8 +14,8 @@ AudioCraft：MusicGen 文本转音乐，AudioGen 文本转声音。
| | |
|---|---|
| 来源 | 可选 — 通过 `hermes skills install official/creative/audiocraft` 安装 |
| 路径 | `optional-skills/creative/audiocraft` |
| 来源 | 可选 — 通过 `hermes skills install official/creative/audiocraft-audio-generation` 安装 |
| 路径 | `optional-skills/creative/audiocraft-audio-generation` |
| 版本 | `1.0.0` |
| 作者 | Orchestra Research |
| 许可证 | MIT |

2
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/optional/creative/creative-heartmula.md
View file

@ -19,7 +19,7 @@ HeartMuLa：基于歌词与标签的类 Suno 歌曲生成。
| 版本 | `1.0.0` |
| 平台 | linux, macos, windows |
| 标签 | `music`, `audio`, `generation`, `ai`, `heartmula`, `heartcodec`, `lyrics`, `songs` |
| 相关 skill | [`audiocraft-audio-generation`](/user-guide/skills/optional/creative/creative-audiocraft), [`songwriting-and-ai-music`](/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
| 相关 skill | [`audiocraft-audio-generation`](/user-guide/skills/optional/creative/creative-audiocraft-audio-generation), [`songwriting-and-ai-music`](/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
## 参考：完整 SKILL.md

10
website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/optional/mlops/mlops-models-segment-anything.md → website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/skills/optional/mlops/mlops-models-segment-anything-model.md
View file

@ -15,7 +15,7 @@ SAM：通过点、框、掩码实现零样本图像分割。
| | |
|---|---|
| 来源 | 可选 — 通过 `hermes skills install official/mlops/segment-anything` 安装 |
| 路径 | `optional-skills/mlops/models/segment-anything` |
| 路径 | `optional-skills/mlops/models/segment-anything-model` |
| 版本 | `1.0.0` |
| 作者 | Orchestra Research |
| 许可证 | MIT |
@ -92,7 +92,7 @@ import numpy as np
from segment_anything import sam_model_registry, SamPredictor
# 加载模型
sam = sam_model_registry["vit_h"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/checkpoint="sam_vit_h_4b8939.pth")
sam = sam_model_registry["vit_h"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/checkpoint="sam_vit_h_4b8939.pth")
sam.to(device="cuda")
# 创建预测器
@ -478,7 +478,7 @@ decoded_mask = mask_utils.decode(rle)
```python
# 在 VRAM 有限时使用较小模型
sam = sam_model_registry["vit_b"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/checkpoint="sam_vit_b_01ec64.pth")
sam = sam_model_registry["vit_b"](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/checkpoint="sam_vit_b_01ec64.pth")
# 批量处理图像
# 在大批量之间清空 CUDA 缓存
@ -513,8 +513,8 @@ mask_generator = SamAutomaticMaskGenerator(
## 参考资料
- **[高级用法](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/references/advanced-usage.md)** - 批处理、微调、集成
- **[故障排查](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything/references/troubleshooting.md)** - 常见问题与解决方案
- **[高级用法](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/references/advanced-usage.md)** - 批处理、微调、集成
- **[故障排查](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/mlops/models/segment-anything-model/references/troubleshooting.md)** - 常见问题与解决方案
## 资源

8
website/sidebars.ts
View file

@ -225,8 +225,8 @@ const sidebars: SidebarsConfig = {
items: [
'user-guide/skills/bundled/mlops/mlops-huggingface-hub',
'user-guide/skills/bundled/mlops/mlops-inference-llama-cpp',
'user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness',
'user-guide/skills/bundled/mlops/mlops-inference-vllm',
'user-guide/skills/bundled/mlops/mlops-evaluation-evaluating-llms-harness',
'user-guide/skills/bundled/mlops/mlops-inference-serving-llms-vllm',
'user-guide/skills/bundled/mlops/mlops-evaluation-weights-and-biases',
],
},
@ -353,7 +353,7 @@ const sidebars: SidebarsConfig = {
key: 'skills-optional-creative',
collapsed: true,
items: [
'user-guide/skills/optional/creative/creative-audiocraft',
'user-guide/skills/optional/creative/creative-audiocraft-audio-generation',
'user-guide/skills/optional/creative/creative-baoyu-article-illustrator',
'user-guide/skills/optional/creative/creative-baoyu-comic',
'user-guide/skills/optional/creative/creative-blender-mcp',
@ -491,7 +491,7 @@ const sidebars: SidebarsConfig = {
'user-guide/skills/optional/mlops/mlops-pytorch-lightning',
'user-guide/skills/optional/mlops/mlops-qdrant',
'user-guide/skills/optional/mlops/mlops-saelens',
'user-guide/skills/optional/mlops/mlops-models-segment-anything',
'user-guide/skills/optional/mlops/mlops-models-segment-anything-model',
'user-guide/skills/optional/mlops/mlops-simpo',
'user-guide/skills/optional/mlops/mlops-slime',
'user-guide/skills/optional/mlops/mlops-stable-diffusion',