Update README.md
Browse files
README.md
CHANGED
@@ -46,7 +46,28 @@ This model is a continued pretraining version of [meta-llama/Llama-3.1-8B-Instru
|
|
46 |
|
47 |
## How to Get Started with the Model
|
48 |
|
49 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
[More Information Needed]
|
52 |
|
@@ -94,7 +115,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
94 |
- **Hardware Type:** 4x NVIDIA A100 SXM4 80 GB (TDP of 400W)
|
95 |
- **Hours used:** 60
|
96 |
- **Cloud Provider:** Private infrastructure
|
97 |
-
- **Carbon Emitted:** 10.37
|
98 |
|
99 |
## Citation
|
100 |
|
|
|
46 |
|
47 |
## How to Get Started with the Model
|
48 |
|
49 |
+
```python
|
50 |
+
import transformers
|
51 |
+
import torch
|
52 |
+
|
53 |
+
model_id = "irlab-udc/Llama-3.1-8B-Instruct-Galician"
|
54 |
+
|
55 |
+
pipeline = transformers.pipeline(
|
56 |
+
"text-generation",
|
57 |
+
model=model_id,
|
58 |
+
model_kwargs={"torch_dtype": torch.bfloat16},
|
59 |
+
device_map="auto",
|
60 |
+
)
|
61 |
+
|
62 |
+
messages = [
|
63 |
+
{"role": "system", "content": "You are a conversational AI that always responds in Galician."},
|
64 |
+
{"role": "user", "content": "Cal é a principal vantaxe de usar Scrum?"},
|
65 |
+
]
|
66 |
+
|
67 |
+
outputs = pipeline(messages, max_new_tokens=512)
|
68 |
+
|
69 |
+
print(outputs[0]["generated_text"][-1]["content"])
|
70 |
+
```
|
71 |
|
72 |
[More Information Needed]
|
73 |
|
|
|
115 |
- **Hardware Type:** 4x NVIDIA A100 SXM4 80 GB (TDP of 400W)
|
116 |
- **Hours used:** 60
|
117 |
- **Cloud Provider:** Private infrastructure
|
118 |
+
- **Carbon Emitted:** 10.37 Kg. CO₂ eq.
|
119 |
|
120 |
## Citation
|
121 |
|