Downloads · 30 days
5
17% of all-time downloads
cap-26m-fast-dev
d2v1shx/cap-26m-fast-dev
cap-26m-fast-dev is a machine learning model from d2v1shx. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Tiny decoder-only language model trained locally on macOS as part of the cap project.
All-time downloads
30
Public
Parameters
29.1M
116 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors116 MB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026
- SHA
- 0eebc377
Model card
From the Hugging Face model README
cap-26m-fast-dev
Tiny decoder-only language model trained locally on macOS as part of the cap project.
Summary
- Model name:
cap-26m-fast-dev - Base architecture: decoder-only Transformer in a LLaMA-style configuration
- Training data: TinyStories
- Training mode: fast development run for quick iteration
Checkpoint notes
- Saved from the
caplocal training pipeline - Includes tokenizer files alongside the model checkpoint
- Intended as an intermediate checkpoint, not a final polished release
Known metrics
- Structured eval loss:
4.8252 - Structured eval perplexity:
124.61
Usage
Load with transformers using AutoModelForCausalLM.from_pretrained(...) and AutoTokenizer.from_pretrained(...).
- Type
- llama
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026