MCPcopy
hub / github.com/jaymody/picoGPT / get_encoder

Function get_encoder

encoder.py:114–120  ·  view source on GitHub ↗
(model_name, models_dir)

Source from the content-addressed store, hash-verified

112
113
114def get_encoder(model_name, models_dir):
115 with open(os.path.join(models_dir, model_name, "encoder.json"), "r") as f:
116 encoder = json.load(f)
117 with open(os.path.join(models_dir, model_name, "vocab.bpe"), "r", encoding="utf-8") as f:
118 bpe_data = f.read()
119 bpe_merges = [tuple(merge_str.split()) for merge_str in bpe_data.split("\n")[1:-1]]
120 return Encoder(encoder=encoder, bpe_merges=bpe_merges)

Callers 1

Calls 1

EncoderClass · 0.85

Tested by

no test coverage detected