Update README.md
Browse files
README.md
CHANGED
@@ -67,4 +67,33 @@ MambaForCausalLM(
|
|
67 |
|
68 |
Concerns:
|
69 |
|
70 |
-
Potential for biased, incorrect, or harmful content generation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
Concerns:
|
69 |
|
70 |
+
Potential for biased, incorrect, or harmful content generation.
|
71 |
+
|
72 |
+
|
73 |
+
|
74 |
+
## **Usage Example**
|
75 |
+
|
76 |
+
To generate text using this model with Hugging Face's `pipeline`, use the following Python code:
|
77 |
+
|
78 |
+
```python
|
79 |
+
from transformers import pipeline
|
80 |
+
|
81 |
+
# Load the model
|
82 |
+
model_name = "NYTK/PULI-HuBA130M"
|
83 |
+
|
84 |
+
# Initialize the text generation pipeline
|
85 |
+
generator = pipeline("text-generation", model=model_name)
|
86 |
+
|
87 |
+
# Generate text with recommended parameters
|
88 |
+
output = generator(
|
89 |
+
"Az a t茅ny, hogy anyanyelvem magyar, 茅s magyarul besz茅lek, gondolkozom, 铆rok, 茅letem legnagyobb esem茅nye, melyhez nincs foghat贸.", # Example prompt in Hungarian
|
90 |
+
max_length=156,
|
91 |
+
do_sample=True,
|
92 |
+
repetition_penalty=1.35,
|
93 |
+
temperature=0.2,
|
94 |
+
top_k=100,
|
95 |
+
top_p=0.99
|
96 |
+
)
|
97 |
+
|
98 |
+
# Print the generated text
|
99 |
+
print(output[0]["generated_text"])
|