Skip to content

Add embedding recipe: build domain-specific embeddings from raw documents #85

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
oliverholworthy wants to merge 10 commits into
base: main
Choose a base branch
from
Open

Add embedding recipe: build domain-specific embeddings from raw documents #85

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
218d001
Add embedding recipe for fine-tuning, evaluation, and deployment
oliverholworthy Mar 10, 2026
58e4f07
docs: Add embedding recipe documentation to docs site
oliverholworthy Mar 25, 2026
3bd29da
Move sample corpus to HuggingFace with hf:// URI support
oliverholworthy Mar 25, 2026
2e23ca7
Fix embed recipe tests: correct CLI module paths and required fields
oliverholworthy Mar 30, 2026
e750933
docs: Fix embed model specs (dimension 2048, max seq len 8192)
oliverholworthy Mar 30, 2026
0ebf6ec
docs: Clarify corpus file formats are configurable, not restricted
oliverholworthy Mar 30, 2026
0ebe71a
fix(embed): use python entrypoint consistently and remove dead variable
oliverholworthy Mar 30, 2026
87cb210
fix(embed): fix file handle leak, export patch, unused import, and docs
oliverholworthy Mar 30, 2026
1217a69
Track uv.lock files and revert eval monkey-patch
oliverholworthy Mar 30, 2026
f23683b
docs(embed): add pre-generated dataset section from embed-finetune-re…
oliverholworthy Mar 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,8 @@ env.bak/
venv.bak/
.venv/

# UV lock files in recipe stages are tracked for reproducible builds

# IDEs
.vscode/
.idea/
Expand Down Expand Up @@ -63,12 +65,14 @@ env.toml
conductor.json

# Project specific
/artifacts/
output/
outputs/
logs/
checkpoints/
data/
!src/nemotron/cli/nano3/data/
!src/nemotron/cli/embed/data/
workspace/
wandb/
.nemotron/
Expand Down
10 changes: 10 additions & 0 deletions docs/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,15 @@ End-to-end applications: RAG agents, ML agents, and multi-agent systems.
**Stages:** Pretraining → SFT → RL
:::

:::{grid-item-card} Embedding Fine-Tuning
:link: nemotron/embed/README
:link-type: doc

Fine-tune Llama-Nemotron-Embed-1B-v2 on domain-specific data with synthetic data generation, evaluation, and NIM deployment.

**Stages:** SDG → Data Prep → Finetune → Eval → Export → Deploy
:::

::::

## Training Pipeline
Expand Down Expand Up @@ -134,6 +143,7 @@ use-case-examples/sql-lora-finetuning-and-deployment/README.md

nemotron/nano3/README.md
nemotron/super3/README.md
nemotron/embed/README.md
nemotron/artifacts.md
```

Expand Down
Loading
Loading