Downloads · 30 days
15
2% of all-time downloads
single-floppy-346k-merged-ONNX
onnx-community/single-floppy-346k-merged-ONNX
single-floppy-346k-merged-ONNX is a text generation model from onnx-community. Use it when you need the model to write or continue text. It is set up for transformers.js. The card lists the license as cc-by-sa-4.0.
This is an ONNX version of NILKNARFGonzo/single-floppy-346k-merged. It was automatically converted and uploaded using this Hugging Face Space.
All-time downloads
831
Public
Repo size
5.9 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx7.9 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers.js
- License
- cc-by-sa-4.0
- Model type
- gpt2
- Access
- Public
- Created
- Aug 7, 2026
- Updated
- Aug 24, 2026
- SHA
- d8b7b064
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
single-floppy-346k-merged (ONNX)
This is an ONNX version of NILKNARFGonzo/single-floppy-346k-merged. It was automatically converted and uploaded using this Hugging Face Space.
Usage with Transformers.js
See the pipeline documentation for text-generation: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TextGenerationPipeline
A weird model trained on a Pi. This model is a standalone version; no need to download anything else.
(This version is an ONNX version made by onnx-community - big thanks to them! If you wouldn't mind, downloading the original would be highly appreciated!)
Training Details
| Category | Specification |
|---|---|
| Model Architecture | GPT‑2 (decoder‑only Transformer) |
| Total Parameters | 346,104 |
| Model Size (FP32) | 1.32 MB (1,387,072 bytes) |
Layers (n_layer) | 2 |
Embedding Dimension (n_embd) | 92 |
Attention Heads (n_head) | 2 |
Context Length (n_positions) | 1024 |
| Vocabulary Size | 502 (byte‑level BPE, tied embeddings) |
| Training Framework | Oobabooga TextGen WebUI (Transformers + PEFT) |
| Fine‑Tuning Method | LoRA (Target all linear layers) |
| LoRA Rank | 8 |
| LoRA Alpha | 16 |
| Optimizer | AdamW 8‑bit (adamw_bnb_8bit) |
| Learning Rate | 2e‑4 (linear scheduler, 20 warmup steps) |
| Batch Size | 4 |
| Training Dataset | Capybara ShareGPT (random subset, 1.36 MB, 1,453,408 bytes) |
| Dataset Format | JSON array with "text" field (flattened ShareGPT) |
| Training Epochs | 5 |
| Loss Target | Stopped at ~6.0 (plateaued due to parameter limit) |
| Hardware | Raspberry Pi 5, 8GB RAM, ARM Cortex‑A76 (CPU only) |
| Training Time | ~1 hour |
| Tokenizer | Custom byte‑level BPE (trained on dataset) |
| Tokenizer Special Tokens | [BOS], [EOS], [PAD], [UNK] |
| Note | This is a proof‑of‑concept model. It fits on a 3.5‑inch floppy disk and was trained from scratch on a Raspberry Pi. |
This thing still produces nonsense. Be warned. Chats should be formatted as:
### User:
<user prompt>
### Assistant:
<assistant response>
- Task
- Text Generation
- Library
- transformers.js
- Type
- gpt2
- License
- cc-by-sa-4.0
- Languages
- en
- Created
- Aug 7, 2026
- Updated
- Aug 24, 2026