Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -11,10 +11,10 @@ title = """
|
|
11 |
description = """
|
12 |
You can use this Space to test out the current model [intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct). e5mistral has a larger context window, a different prompting/return mechanism and generally better results than other embedding models.
|
13 |
You can also use 🐣e5-mistral🛌🏻 by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/e5?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3>
|
14 |
-
Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community on 👻Discord: [](https://discord.gg/GWpVpekp) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Polytonic](https://github.com/tonic-ai) & contribute to 🌟 [Poly](https://github.com/tonic-ai/poly)
|
15 |
"""
|
16 |
|
17 |
-
os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:
|
18 |
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
19 |
|
20 |
# torch.backends.cuda.matmul.allow_tf32 = True
|
@@ -38,7 +38,7 @@ def get_detailed_instruct(task_description: str, query: str) -> str:
|
|
38 |
def compute_embeddings(*input_texts):
|
39 |
tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-mistral-7b-instruct')
|
40 |
model = AutoModel.from_pretrained('intfloat/e5-mistral-7b-instruct', torch_dtype=torch.float16, device_map=device)
|
41 |
-
max_length =
|
42 |
task = 'Given a web search query, retrieve relevant passages that answer the query'
|
43 |
processed_texts = [get_detailed_instruct(task, text) for text in input_texts]
|
44 |
batch_dict = tokenizer(processed_texts, max_length=max_length - 1, return_attention_mask=False, padding=False, truncation=True)
|
|
|
11 |
description = """
|
12 |
You can use this Space to test out the current model [intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct). e5mistral has a larger context window, a different prompting/return mechanism and generally better results than other embedding models.
|
13 |
You can also use 🐣e5-mistral🛌🏻 by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/e5?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3>
|
14 |
+
Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community on 👻Discord: [](https://discord.gg/GWpVpekp) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Polytonic](https://github.com/tonic-ai) & contribute to 🌟 [Poly](https://github.com/tonic-ai/poly) 🤗Big thanks to the folks at huggingface for the GPUZero access !🚀
|
15 |
"""
|
16 |
|
17 |
+
os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:30'
|
18 |
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
19 |
|
20 |
# torch.backends.cuda.matmul.allow_tf32 = True
|
|
|
38 |
def compute_embeddings(*input_texts):
|
39 |
tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-mistral-7b-instruct')
|
40 |
model = AutoModel.from_pretrained('intfloat/e5-mistral-7b-instruct', torch_dtype=torch.float16, device_map=device)
|
41 |
+
max_length = 2042
|
42 |
task = 'Given a web search query, retrieve relevant passages that answer the query'
|
43 |
processed_texts = [get_detailed_instruct(task, text) for text in input_texts]
|
44 |
batch_dict = tokenizer(processed_texts, max_length=max_length - 1, return_attention_mask=False, padding=False, truncation=True)
|