Files
figment-finetuned-model-arc…/v2-20260609-merged-bf16
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
..

base_model, base_model_relation, library_name, pipeline_tag, license, license_name, license_link, language, tags
base_model base_model_relation library_name pipeline_tag license license_name license_link language tags
nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 finetune transformers text-generation other nvidia-nemotron-open-model-license https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/
en
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.