Update README.md
Browse filesAdded Karpathy's well-earned credentials.
README.md
CHANGED
|
@@ -18,7 +18,8 @@ spaces:
|
|
| 18 |
|
| 19 |
# PicoChat
|
| 20 |
|
| 21 |
-
**PicoChat** is a 335M parameter language model trained entirely from scratch on a MacBook Air M2 (16GB RAM) in approximately 6 days.
|
|
|
|
| 22 |
It serves as a "lab notebook" proof-of-concept for training capable small language models (SLMs) on consumer hardware using pure PyTorch and MPS (Metal Performance Shaders).
|
| 23 |
|
| 24 |
> **Links:**
|
|
@@ -77,7 +78,7 @@ The model was trained in three phases using the [nanochat](https://github.com/ka
|
|
| 77 |
|
| 78 |
## Usage
|
| 79 |
|
| 80 |
-
This model requires the [
|
| 81 |
|
| 82 |
## License
|
| 83 |
|
|
|
|
| 18 |
|
| 19 |
# PicoChat
|
| 20 |
|
| 21 |
+
**PicoChat** is a 335M parameter language model trained entirely from scratch on a MacBook Air M2 (16GB RAM) in approximately 6 days. The code is based on Andrej Karpathy's
|
| 22 |
+
[NanoChat](https://github.com/karpathy/nanochat) and was updated to run at M2 MacBook Air at [PicoChat](https://github.com/MichalGow/PicoChat).
|
| 23 |
It serves as a "lab notebook" proof-of-concept for training capable small language models (SLMs) on consumer hardware using pure PyTorch and MPS (Metal Performance Shaders).
|
| 24 |
|
| 25 |
> **Links:**
|
|
|
|
| 78 |
|
| 79 |
## Usage
|
| 80 |
|
| 81 |
+
This model requires the [picochat](https://github.com/MichalGow/PicoChat) library to run, as it uses a custom architecture implementation optimized for educational clarity and hackability.
|
| 82 |
|
| 83 |
## License
|
| 84 |
|