Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,26 @@ tags: []
|
|
11 |
|
12 |
## Model Details
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
### Model Description
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
11 |
|
12 |
## Model Details
|
13 |
|
14 |
+
### Code to generate the model
|
15 |
+
|
16 |
+
```py
|
17 |
+
from transformers import GraniteMoeConfig, GraniteMoeForCausalLM, AutoTokenizer
|
18 |
+
|
19 |
+
model = GraniteMoeForCausalLM(GraniteMoeConfig(
|
20 |
+
hidden_size=32,
|
21 |
+
intermediate_size=64,
|
22 |
+
num_attention_heads=4,
|
23 |
+
num_hidden_layers=2,
|
24 |
+
num_key_value_heads=4,
|
25 |
+
pad_token_id=0,
|
26 |
+
vocab_size=49155,
|
27 |
+
))
|
28 |
+
tokenizer = AutoTokenizer.from_pretrained('ibm-granite/granite-3.0-1b-a400m-instruct')
|
29 |
+
|
30 |
+
model.push_to_hub('hf-internal-testing/tiny-random-GraniteMoeForCausalLM')
|
31 |
+
tokenizer.push_to_hub('hf-internal-testing/tiny-random-GraniteMoeForCausalLM')
|
32 |
+
```
|
33 |
+
|
34 |
### Model Description
|
35 |
|
36 |
<!-- Provide a longer summary of what this model is. -->
|