mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(docs): unbreak docs-site-checks — ascii-guard diagram + MDX <1% (#12984)

Browse source 
* fix(docs): unbreak ascii-guard lint on github-pr-review-agent diagram

The intro diagram used 4 side-by-side boxes in one row. ascii-guard can't
parse that layout — it reads the whole thing as one 80-wide outer box and
flags the inner box borders at columns 17/39/60 as 'extra characters after
right border'. Per the ascii-guard-lint-fixing skill, the only fix is to
merge into a single outer box.

Rewritten as one 69-char outer box with four labeled regions separated by
arrows. Same semantic content, lint-clean.

Was blocking docs-site-checks CI as 'action_required' across multiple PRs
(see e.g. run 24661820677).

* fix(docs): backtick-wrap `<1%` to avoid MDX JSX parse error

Docusaurus MDX parses `<1%` as the start of a JSX tag, but `1` isn't a
valid tag-name start so compilation fails with 'Unexpected character `1`
(U+0031) before name'. Wrap in backticks so MDX treats it as literal code
text.

Found by running Build Docusaurus step on the PR that unblocked the
ascii-guard step; full docs tree scanned for other `<digit>` patterns
outside backticks/fences, only this one was unsafe.
This commit is contained in:
Teknium 2026-04-20 04:29:02 -07:00 • committed by GitHub
parent e04a55f37f
commit 9a57aa2b1f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 10 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
website/docs/reference/optional-skills-catalog.md
View file

@ -110,7 +110,7 @@ The largest optional category — covers the full ML pipeline from data curation
| **llava** | Large Language and Vision Assistant — visual instruction tuning and image-based conversations combining CLIP vision with LLaMA language models. |
| **modal** | Serverless GPU cloud platform for running ML workloads. On-demand GPU access without infrastructure management, ML model deployment as APIs, or batch jobs with automatic scaling. |
| **nemo-curator** | GPU-accelerated data curation for LLM training. Fuzzy deduplication (16x faster), quality filtering (30+ heuristics), semantic dedup, PII redaction. Scales with RAPIDS. |
| **peft-fine-tuning** | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Train <1% of parameters with minimal accuracy loss for 7B–70B models on limited GPU memory. HuggingFace's official PEFT library. |
| **peft-fine-tuning** | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Train `<1%` of parameters with minimal accuracy loss for 7B–70B models on limited GPU memory. HuggingFace's official PEFT library. |
| **pinecone** | Managed vector database for production AI. Auto-scaling, hybrid search (dense + sparse), metadata filtering, and low latency (under 100ms p95). |
| **pytorch-fsdp** | Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP — parameter sharding, mixed precision, CPU offloading, FSDP2. |
| **pytorch-lightning** | High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks, and minimal boilerplate. |