Downloads · 30 days
14
25% of all-time downloads
bartholomew-sft
jbduran/bartholomew-sft
bartholomew-sft is a machine learning model from jbduran. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
The instruction-tuned BART: a 2.8B-parameter model whose knowledge ends in 1930, fine-tuned to hold a conversation in period-appropriate voice.
All-time downloads
55
Public
Repo size
20.5 GB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.pt20.5 GB · 100%
At a glance
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- eb902ffc
Model card
From the Hugging Face model README
BART SFT
The instruction-tuned BART: a 2.8B-parameter model whose knowledge ends in 1930, fine-tuned to hold a conversation in period-appropriate voice.
📝 Read the write-up · 🌐 Unbounded Labs
Run Think.Unbounded-d32-v2mix-cont-pre1930-curriculum-c3-robust-v2, branched from
BART at base step 9,600.
Specifications
| Base model | bart @ step 9,600 |
| Parameters | 2,818,575,450 (~2.8B, including embeddings) |
| Final step | 42 |
| Validation bpb | 0.7037 |
| Recipe | curriculum (C3Rv2, staged) |
Contents
checkpoints/model_000042.pt final weights (8.99 GB)
checkpoints/optim_000042_rank0.pt
checkpoints/meta_000042.json
checkpoints/eval_metrics.json
config.json full SFT configuration
run.json lineage record
evals/chatcore.json
The curriculum
Training runs in three staged passes over the task routes, with a 30% noise rate throughout, then a robustness pass.
| Stage | Routes | Authentic data |
|---|---|---|
| 1 | knowledge_qa | single-turn |
| 2 | reasoning_qa, stem_reasoning, how_to_qa, opinion_qa, composition_qa, verse_qa | calibration QA |
| 3 | multiturn_qa, narrative_grounded, narrative_fiction | multi-turn |
The robustness pass (1 epoch) adds conversation_qa, unparseable_qa, typo_qa, era_qa, and
conversation_multiturn — teaching the model to cope with malformed input, typos, and questions
about its own era.
Training data
| Dataset | Role |
|---|---|
| synthetic-pre1930-sft | the task routes (~416K rows, eleven routes) |
| authentic-pre1930-sft-conversational | authentic single- and multi-turn rows from 27 public-domain texts |
| vintage-sft-robustness | the robustness pass (7,338 rows, five categories) |
Evaluation
ChatCORE (karpathy suite) at step 42:
| Task | Score |
|---|---|
| ARC-Easy | 0.2458 |
| ARC-Challenge | 0.2304 |
| MMLU | 0.2314 |
| GSM8K | 0.0000 |
| HumanEval | 0.0000 |
| ChatCORE | -0.0113 |
These are modern benchmarks, and the multiple-choice scores sit at chance. That is the expected result for a 2.8B model that has never seen a word written after 1930 — GSM8K and HumanEval in particular test knowledge and formats that simply are not in the training data. The period-adapted suites (vintage-core, vintage-gsm8k, history-event-reconstruction) exist precisely because these numbers don't measure what the model was built to do.
Related
bart (base) · bart-experiments (all 39 runs, including five other SFT variants) · bart-dataset-v3 · bart-midtrain
License
MIT
Built by Unbounded Labs.
- Library
- pytorch
- License
- mit
- Languages
- en
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026