Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -23,7 +23,7 @@ This model is part of the [StepLaw-N_1.0B-D_19.0B](https://huggingface.co/collec
|
|
| 23 |
- **Feed-forward network size (FFN)**: 8192
|
| 24 |
- **Attention heads**: 16
|
| 25 |
- **Layers**: 16
|
| 26 |
-
- **Parameter count**: 1.
|
| 27 |
|
| 28 |
### Training Parameters
|
| 29 |
- **Learning rate (lr)**: 3.453e-04
|
|
@@ -48,7 +48,4 @@ model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
|
|
| 48 |
inputs = tokenizer("A long time ago in a galaxy far, far away", return_tensors="pt")
|
| 49 |
outputs = model.generate(**inputs, max_length=100)
|
| 50 |
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
StepLaw is an initiative to provide thousands of models for optimal hyperparameter research.
|
| 54 |
-
Visit [StepLaw Project](https://step-law.github.io/) for more information.
|
|
|
|
| 23 |
- **Feed-forward network size (FFN)**: 8192
|
| 24 |
- **Attention heads**: 16
|
| 25 |
- **Layers**: 16
|
| 26 |
+
- **Parameter count**: 1.1B
|
| 27 |
|
| 28 |
### Training Parameters
|
| 29 |
- **Learning rate (lr)**: 3.453e-04
|
|
|
|
| 48 |
inputs = tokenizer("A long time ago in a galaxy far, far away", return_tensors="pt")
|
| 49 |
outputs = model.generate(**inputs, max_length=100)
|
| 50 |
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 51 |
+
```
|
|
|
|
|
|
|
|
|