Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
- en
|
| 4 |
license: mit
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# An xLSTM Model
|
|
@@ -24,7 +26,7 @@ conda activate xlstm
|
|
| 24 |
```python
|
| 25 |
from transformers import AutoModelForCasualLM, AutoTokenizer
|
| 26 |
|
| 27 |
-
model_name_or_path = "PatrickHaller/
|
| 28 |
|
| 29 |
model = AutoModelForCasualLM.from_pretrained(model_name_or_path)
|
| 30 |
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
|
|
@@ -36,3 +38,9 @@ generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
|
| 36 |
print(generated_text)
|
| 37 |
|
| 38 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
- en
|
| 4 |
license: mit
|
| 5 |
+
datasets:
|
| 6 |
+
- PatrickHaller/wiki-and-book-corpus-500M
|
| 7 |
---
|
| 8 |
|
| 9 |
# An xLSTM Model
|
|
|
|
| 26 |
```python
|
| 27 |
from transformers import AutoModelForCasualLM, AutoTokenizer
|
| 28 |
|
| 29 |
+
model_name_or_path = "PatrickHaller/xlstm_wikipedia_110M_500M"
|
| 30 |
|
| 31 |
model = AutoModelForCasualLM.from_pretrained(model_name_or_path)
|
| 32 |
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
|
|
|
|
| 38 |
print(generated_text)
|
| 39 |
|
| 40 |
```
|
| 41 |
+
|
| 42 |
+
## Evaluation
|
| 43 |
+
|
| 44 |
+
We evaluated all xLSTM wikipedia models on common zero-shot LM benchmarks:
|
| 45 |
+
|
| 46 |
+
|