Text Generation
Transformers
Safetensors
English
llama
small-language-model
efficient
edge-deployment
speculative-decoding
tiny-model
12m-parameters
kaggle-trained
educational
research
low-resource
cpu-inference
mobile-deployment
preview
stentor2
tokenmonster
Eval Results (legacy)
text-generation-inference
Update load_stentor2.py
Browse files- load_stentor2.py +2 -0
load_stentor2.py
CHANGED
|
@@ -9,6 +9,8 @@ MODEL_ID = "StentorLabs/Stentor2-12M-Preview"
|
|
| 9 |
|
| 10 |
class _Tokenizer:
|
| 11 |
def __init__(self, vocab_path):
|
|
|
|
|
|
|
| 12 |
import tokenmonster
|
| 13 |
self._vocab = tokenmonster.load(vocab_path)
|
| 14 |
self._vocab.add_special_token("</s>")
|
|
|
|
| 9 |
|
| 10 |
class _Tokenizer:
|
| 11 |
def __init__(self, vocab_path):
|
| 12 |
+
import subprocess, sys
|
| 13 |
+
subprocess.run([sys.executable, "-m", "pip", "install", "tokenmonster", "-q"], check=True)
|
| 14 |
import tokenmonster
|
| 15 |
self._vocab = tokenmonster.load(vocab_path)
|
| 16 |
self._vocab.add_special_token("</s>")
|