lopace 0.1.2__py3-none-any.whl → 0.1.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: lopace
3
- Version: 0.1.2
3
+ Version: 0.1.3
4
4
  Summary: Lossless Optimized Prompt Accurate Compression Engine
5
5
  Home-page: https://github.com/connectaman/LoPace
6
6
  Author: Aman Ulla
@@ -8,6 +8,8 @@ License: MIT
8
8
  Project-URL: Homepage, https://github.com/connectaman/LoPace
9
9
  Project-URL: Repository, https://github.com/connectaman/LoPace
10
10
  Project-URL: Issues, https://github.com/connectaman/LoPace/issues
11
+ Project-URL: PyPI, https://pypi.org/project/lopace/
12
+ Project-URL: Hugging Face Spaces, https://huggingface.co/spaces/codewithaman/LoPace
11
13
  Keywords: prompt,compression,tokenization,zstd,bpe,nlp
12
14
  Classifier: Development Status :: 4 - Beta
13
15
  Classifier: Intended Audience :: Developers
@@ -31,12 +33,18 @@ Dynamic: requires-python
31
33
 
32
34
  # LoPace
33
35
 
36
+ <div align="center">
37
+ <img src="screenshots/logo-text.png" alt="LoPace Logo" width="600"/>
38
+ </div>
39
+
34
40
  **Lossless Optimized Prompt Accurate Compression Engine**
35
41
 
36
42
  A professional, open-source Python package for compressing and decompressing prompts using multiple techniques: Zstd, Token-based (BPE), and Hybrid methods. Achieve up to 80% space reduction while maintaining perfect lossless reconstruction.
37
43
 
38
44
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
39
45
  [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
46
+ [![PyPI version](https://badge.fury.io/py/lopace.svg)](https://pypi.org/project/lopace/)
47
+ [![🤗 Spaces](https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/codewithaman/LoPace)
40
48
 
41
49
  ## The Problem: Storage Challenges with Large Prompts
42
50
 
@@ -310,6 +318,7 @@ Comprehensive benchmarks were conducted on 10 diverse prompts across three size
310
318
  ### Speed & Throughput Metrics
311
319
 
312
320
  ![Speed Metrics](screenshots/speed_metrics.svg)
321
+ ![Speed Metrics](screenshots/original_vs_decompressed.svg)
313
322
 
314
323
  **Key Insights:**
315
324
  - **Compression speeds range from 50-200 MB/s** depending on method and prompt size
@@ -1,11 +1,11 @@
1
1
  lopace/__init__.py,sha256=PYjZWZHhSITNgag9sF0qZ_yXgZaMa3R8_3FuasiH0Nc,351
2
2
  lopace/compressor.py,sha256=nUTWDcAPYvQaeSFKx_lne-D2xIQ02IMVGE4yLODo8qE,19060
3
- lopace-0.1.2.dist-info/licenses/LICENSE,sha256=uFUrlsfsOwx_8Nzhq2pUgNaJghcJxXBMML3l7T39Tm0,1067
3
+ lopace-0.1.3.dist-info/licenses/LICENSE,sha256=uFUrlsfsOwx_8Nzhq2pUgNaJghcJxXBMML3l7T39Tm0,1067
4
4
  scripts/__init__.py,sha256=XLq0VmLoEBfnWjzYmxb_JRzAIqwZDv-2s10TO692TLc,59
5
5
  scripts/generate_visualizations.py,sha256=AJm2DNs-tiwdTHLivEQL9QkztmCclgGT1u4ds5QY4BQ,41812
6
6
  tests/__init__.py,sha256=yXNVJE20E2iHo0qbit5SgRE35eXWq89F1kkhNHy7VJA,31
7
7
  tests/test_compressor.py,sha256=-vMztSzY89n5dpShcACrFboEQOlfJ6FxF7eQOEU3swM,8273
8
- lopace-0.1.2.dist-info/METADATA,sha256=whyhaCEK3DUl9mbZ9d-0u-AvpbwkiblkBWPj7gAi5yw,18096
9
- lopace-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
10
- lopace-0.1.2.dist-info/top_level.txt,sha256=k-gL-51ulMq50vhNS91c1eyGRNse0vs_PzS9VdAiYlw,21
11
- lopace-0.1.2.dist-info/RECORD,,
8
+ lopace-0.1.3.dist-info/METADATA,sha256=YhcHwNH6kR9exmyoITfc3LldbhaSxIdtDKeVZIVON88,18612
9
+ lopace-0.1.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
10
+ lopace-0.1.3.dist-info/top_level.txt,sha256=k-gL-51ulMq50vhNS91c1eyGRNse0vs_PzS9VdAiYlw,21
11
+ lopace-0.1.3.dist-info/RECORD,,
File without changes