Files
ModelHub XC 54ab68d505 初始化项目,由ModelHub XC社区提供模型
Model: build-small-hackathon/figment-finetuned-model-archive
Source: Original Platform
2026-08-13 17:17:17 +08:00

34 lines
1.3 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
- v3
- protocol-navigation
- synthetic-data
- not-for-clinical-use
---
# Figment SFT v3 Merged BF16
This directory contains the `figment_sft_v3` Figment local-model checkpoint merged into `nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16`.
- Base model: `nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16`
- Merge method: `peft.merge_and_unload(safe_merge=True)`
- Dtype: BF16
- Source adapter path: `/checkpoints/figment_sft_v3/figment-sft-v3-lora`
- Merged output path: `/checkpoints/figment_sft_v3/figment-sft-v3-lora-merged-bf16`
- Merged manifest SHA-256: `d18e72fb258764321ec17abd687af7214a480f491f11d83cf64e38824dc4e510`
This is a prototype protocol-navigation model for synthetic/de-identified Figment scenarios. It is not a medical device and must not be used for clinical care, diagnosis, prescribing, autonomous triage, or replacing local protocol and trained responder review.
The artifact is derived from the NVIDIA base model and is governed by the upstream NVIDIA Nemotron Open Model License.