68 lines
2.4 KiB
Markdown
68 lines
2.4 KiB
Markdown
---
|
|
base_model: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
|
|
base_model_relation: finetune
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
license: other
|
|
license_name: nvidia-nemotron-open-model-license
|
|
license_link: >-
|
|
https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/
|
|
language:
|
|
- en
|
|
tags:
|
|
- figment
|
|
- v2
|
|
- merged-bf16
|
|
- protocol-navigation
|
|
- synthetic-data
|
|
- not-for-clinical-use
|
|
---
|
|
|
|
# Figment SFT V2 Merged BF16
|
|
|
|
This directory contains the `figment_sft_v2` LoRA adapter merged into `nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16` with `peft.merge_and_unload(safe_merge=True)`.
|
|
|
|
## Artifact Summary
|
|
|
|
- Source adapter: `/checkpoints/figment_sft_v2/figment-sft-v2-lora`
|
|
- Merged output: `/checkpoints/figment_sft_v2/figment-sft-v2-lora-merged-bf16`
|
|
- Merge dtype: BF16
|
|
- Base model: `nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16`
|
|
- Merged manifest SHA-256: `6885f758f30a76e798fac73ebedd64684f3287d6b459f2b625029b03031179dc`
|
|
- HF shard 1 SHA-256: `9e224445985294263fce0437f82e55d116e90f5f19a5b995d47ee5081ff97c63`
|
|
- HF shard 2 SHA-256: `758eb779adf5379fb96ea42c4c38cfc6de9dc3d53c4e3863a7aea15ccebae5ae`
|
|
- Matching GGUF file: `../v2-20260609-merged-bf16.gguf`
|
|
- GGUF SHA-256: `281251bf326bfef219fe213cf01d7457164972ce2f99067b0ccc1fdb5821ea01`
|
|
|
|
## Training Data
|
|
|
|
The adapter was trained on the synthetic/de-identified `figment_sft_v2` corpus:
|
|
|
|
- Total rows: 1500
|
|
- Train rows: 1352
|
|
- Validation rows: 148
|
|
- Navigator-full rows: 1000
|
|
- Focused-repair rows: 500
|
|
- Train split SHA-256: `27233926a2bd9320418ff10b0c14f3885834adf2f48865ee469c939e2ffeb68a`
|
|
- Validation split SHA-256: `7964c75cd3940a8549e6b8b2ef15b4d5cd45e8607af8f77a4982ffe01116bfb4`
|
|
|
|
The corpus is published in the dataset repository `build-small-hackathon/figment-eval-traces` as the `figment_sft_v2` config.
|
|
|
|
## Evaluation
|
|
|
|
The local 50-case evaluation run was `local_4b_v2_lora_20260609T103344Z`:
|
|
|
|
| Metric | Value |
|
|
| --- | ---: |
|
|
| Total cases | 50 |
|
|
| Competence successes | 33/50 |
|
|
| Raw configured-model successes | 33/50 |
|
|
| Focused-repair successes | 0 |
|
|
| Full fallback uses | 0 |
|
|
| Final validation successes | 50/50 |
|
|
| Model-visible fields retained | 627/650 |
|
|
|
|
## Safety
|
|
|
|
Prototype artifact only. This checkpoint is not a medical device and must not be used for diagnosis, prescribing, medication dosing, autonomous triage, or replacing local protocol, clinician judgment, supervisor review, or trained responder review.
|