riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

gguf conversion add_prefix_space=None for llama3 (#31937)

Browse Source 
* gguf conversion forces add_prefix_space=False for llama3, this is not required and forces from_slow, which fails. changing to None + test

* typo

* clean test
This commit is contained in:
Ita Zaporozhets 2024-07-23 11:45:54 +02:00 committed by GitHub
parent 2e113422b3
commit a1844a3209
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/integrations/ggml.py
View File

@ -609,7 +609,7 @@ class GGUFLlamaConverter(LlamaConverter):
self.additional_kwargs["bos_token"] = eos_token
if self.is_llama_3_tokenizer:
self.additional_kwargs["add_prefix_space"] = False
self.additional_kwargs["add_prefix_space"] = None
self.additional_kwargs["clean_up_tokenization_spaces"] = True
self.additional_kwargs["legacy"] = False

11
tests/quantization/ggml/test_ggml.py
View File

@ -174,10 +174,13 @@ class GgufIntegrationTests(unittest.TestCase):
self.assertEqual(tokenizer.decode(out[0], skip_special_tokens=True), EXPECTED_TEXT)
def test_llama3_q4_0_tokenizer(self):
tokenizer_gguf = AutoTokenizer.from_pretrained(self.llama3_model_id, gguf_file=self.q4_llama3_model_id)
special_sentence = "สวัสดี"
predicted_text = tokenizer_gguf.decode(tokenizer_gguf.encode(special_sentence, return_tensors="pt")[0])
self.assertEqual(predicted_text, "<|begin_of_text|>" + special_sentence)
tokenizer = AutoTokenizer.from_pretrained(self.llama3_model_id, gguf_file=self.q4_llama3_model_id)
with tempfile.TemporaryDirectory() as tmpdirname:
tokenizer.save_pretrained(tmpdirname)
tokenizer = AutoTokenizer.from_pretrained(tmpdirname)
special_sentence = "สวัสดี"
predicted_text = tokenizer.decode(tokenizer.encode(special_sentence, return_tensors="pt")[0])
self.assertEqual(predicted_text, "<|begin_of_text|>" + special_sentence)
def test_llama3_q4_0(self):
tokenizer = AutoTokenizer.from_pretrained(self.llama3_model_id, gguf_file=self.q4_llama3_model_id)