mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 23:12:07 +00:00
04e1af94d7
* feat: first draft load multiple lora * feat: load weights within layer and refactor lora pass * fix: refactor and reduce lora math * feat: baseline impl single request multi lora support * feat: prefer lorax implementation and port loading logic * fix: prefer adapter_data and refactors * feat: perfer loraxs custom punica kernels and add mlp loras * fix: adjust batch for bgmv * fix: adjust adapter_segments logic when in batch * fix: refactor and move changes to v3 proto * fix: pass model_id for all flash causal lms * fix: pass model_id for all causal and seq2seq lms * fix: add model_id to model test * feat: add lora support to mistral and refactors * feat: prefer model id in request * fix: include rust code for adapter id * feat: bump launcher and add new lora docs * feat: support base model generation and refactors * fix: rename doc to retry ci build * feat: support if vlm models * fix: add adapter_data param and avoid missing layers * fix: add adapter_data param to phi and neox * fix: update all models forwards to include adapter_data * fix: add model_id to IdeficsCausalLM * Update lora.md Fixed a typo * Update lora.md Fixing spam image * fix: add lora kernel to dockerfile, support running without kernels and refactors * fix: avoid dockerfile conflict * fix: refactors and adjust flash llama lora logic * fix: skip llama test due to CI issue (temp) * fix: skip llama test CI (temp) 2 * fix: revert skips and prefer updated ci token for tests * fix: refactors and helpful comments * fix: add noop in TensorParallelAdapterRowLinear too * fix: refactor and move shard_lora_weights logic * fix: exit early if no adapter_data --------- Co-authored-by: Derek <datavistics@gmail.com>
84 lines
1.8 KiB
Python
84 lines
1.8 KiB
Python
import pytest
|
|
import torch
|
|
|
|
from transformers import AutoTokenizer
|
|
|
|
from text_generation_server.models import Model
|
|
|
|
|
|
def get_test_model():
|
|
class TestModel(Model):
|
|
def batch_type(self):
|
|
raise NotImplementedError
|
|
|
|
def generate_token(self, batch):
|
|
raise NotImplementedError
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("huggingface/llama-7b")
|
|
|
|
model = TestModel(
|
|
"test_model_id",
|
|
torch.nn.Linear(1, 1),
|
|
tokenizer,
|
|
False,
|
|
torch.float32,
|
|
torch.device("cpu"),
|
|
)
|
|
return model
|
|
|
|
|
|
@pytest.mark.private
|
|
def test_decode_streaming_english_spaces():
|
|
model = get_test_model()
|
|
truth = "Hello here, this is a simple test"
|
|
all_input_ids = [15043, 1244, 29892, 445, 338, 263, 2560, 1243]
|
|
assert (
|
|
all_input_ids == model.tokenizer(truth, add_special_tokens=False)["input_ids"]
|
|
)
|
|
|
|
decoded_text = ""
|
|
offset = 0
|
|
token_offset = 0
|
|
for i in range(len(all_input_ids)):
|
|
text, offset, token_offset = model.decode_token(
|
|
all_input_ids[: i + 1], offset, token_offset
|
|
)
|
|
decoded_text += text
|
|
|
|
assert decoded_text == truth
|
|
|
|
|
|
@pytest.mark.private
|
|
def test_decode_streaming_chinese_utf8():
|
|
model = get_test_model()
|
|
truth = "我很感谢你的热情"
|
|
all_input_ids = [
|
|
30672,
|
|
232,
|
|
193,
|
|
139,
|
|
233,
|
|
135,
|
|
162,
|
|
235,
|
|
179,
|
|
165,
|
|
30919,
|
|
30210,
|
|
234,
|
|
134,
|
|
176,
|
|
30993,
|
|
]
|
|
|
|
decoded_text = ""
|
|
offset = 0
|
|
token_offset = 0
|
|
for i in range(len(all_input_ids)):
|
|
text, offset, token_offset = model.decode_token(
|
|
all_input_ids[: i + 1], offset, token_offset
|
|
)
|
|
decoded_text += text
|
|
|
|
assert decoded_text == truth
|