mathformer 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

mathformer/addformer/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 64,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 27
+}

mathformer/addformer/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

mathformer/addformer/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/addformer/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "MathTokenizer",
+  "model_max_length": 64,
+  "padding_side": "right",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/addformer/vocab.json

@@ -0,0 +1,29 @@
+{
+  "<pad>": 0,
+  "<s>": 1,
+  "</s>": 2,
+  "<unk>": 3,
+  "0": 4,
+  "1": 5,
+  "2": 6,
+  "3": 7,
+  "4": 8,
+  "5": 9,
+  "6": 10,
+  "7": 11,
+  "8": 12,
+  "9": 13,
+  "+": 14,
+  "-": 15,
+  "*": 16,
+  "/": 17,
+  "=": 18,
+  ".": 19,
+  "(": 20,
+  ")": 21,
+  "^": 22,
+  "%": 23,
+  " ": 24,
+  "Q": 25,
+  "R": 26
+}

mathformer/divformer/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 64,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 27
+}

mathformer/divformer/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

mathformer/divformer/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/divformer/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "MathTokenizer",
+  "model_max_length": 64,
+  "padding_side": "right",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/divformer/vocab.json

@@ -0,0 +1,29 @@
+{
+  "<pad>": 0,
+  "<s>": 1,
+  "</s>": 2,
+  "<unk>": 3,
+  "0": 4,
+  "1": 5,
+  "2": 6,
+  "3": 7,
+  "4": 8,
+  "5": 9,
+  "6": 10,
+  "7": 11,
+  "8": 12,
+  "9": 13,
+  "+": 14,
+  "-": 15,
+  "*": 16,
+  "/": 17,
+  "=": 18,
+  ".": 19,
+  "(": 20,
+  ")": 21,
+  "^": 22,
+  "%": 23,
+  " ": 24,
+  "Q": 25,
+  "R": 26
+}

mathformer/mulformer/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 64,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 27
+}

mathformer/mulformer/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

mathformer/mulformer/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/mulformer/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "MathTokenizer",
+  "model_max_length": 64,
+  "padding_side": "right",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/mulformer/vocab.json

@@ -0,0 +1,29 @@
+{
+  "<pad>": 0,
+  "<s>": 1,
+  "</s>": 2,
+  "<unk>": 3,
+  "0": 4,
+  "1": 5,
+  "2": 6,
+  "3": 7,
+  "4": 8,
+  "5": 9,
+  "6": 10,
+  "7": 11,
+  "8": 12,
+  "9": 13,
+  "+": 14,
+  "-": 15,
+  "*": 16,
+  "/": 17,
+  "=": 18,
+  ".": 19,
+  "(": 20,
+  ")": 21,
+  "^": 22,
+  "%": 23,
+  " ": 24,
+  "Q": 25,
+  "R": 26
+}

mathformer/subformer/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 64,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 27
+}

mathformer/subformer/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

mathformer/subformer/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/subformer/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "MathTokenizer",
+  "model_max_length": 64,
+  "padding_side": "right",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

mathformer/subformer/vocab.json

@@ -0,0 +1,29 @@
+{
+  "<pad>": 0,
+  "<s>": 1,
+  "</s>": 2,
+  "<unk>": 3,
+  "0": 4,
+  "1": 5,
+  "2": 6,
+  "3": 7,
+  "4": 8,
+  "5": 9,
+  "6": 10,
+  "7": 11,
+  "8": 12,
+  "9": 13,
+  "+": 14,
+  "-": 15,
+  "*": 16,
+  "/": 17,
+  "=": 18,
+  ".": 19,
+  "(": 20,
+  ")": 21,
+  "^": 22,
+  "%": 23,
+  " ": 24,
+  "Q": 25,
+  "R": 26
+}

mathformer-1.0.1.dist-info/METADATA

@@ -0,0 +1,124 @@
+Metadata-Version: 2.4
+Name: mathformer
+Version: 1.0.1
+Summary: A transformer-based math library
+Author-email: JeremySu0818 <xinghong.su0818@gmail.com>
+Project-URL: Homepage, https://github.com/JeremySu0818/MathFormer-API
+Project-URL: Bug Tracker, https://github.com/JeremySu0818/MathFormer-API/issues
+Project-URL: Repository, https://github.com/JeremySu0818/MathFormer-API
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: transformers>=4.30.0
+Requires-Dist: safetensors>=0.3.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Dynamic: license-file
+
+# MathFormer
+
+MathFormer is a Python library that leverages Transformer-based language models to perform mathematical operations. Unlike standard arithmetic libraries, MathFormer uses Llama-architecture models to "predict" the results of arithmetic operations, token by token, demonstrating the capability of small language models to learn arithmetic rules.
+
+It supports basic arithmetic operations: **Addition**, **Subtraction**, **Multiplication**, and **Division**.
+
+## Features
+
+- **Transformer-Powered Arithmetic**: Uses specialized Llama-based models for each arithmetic operation.
+- **Large Number Support**: Implements recursive logic to handle multi-digit arithmetic using digit-by-digit prediction (similar to manual calculation).
+- **Unified API**: Easy-to-use functions for `add`, `sub`, `mul`, and `div`.
+- **Resource Management**: Supports lazy loading of models to save memory, and manual unloading.
+- **Custom Tokenizer**: Built-in minimalist tokenizer optimized for mathematical expressions.
+
+## Installation
+
+You can install MathFormer via pip:
+
+```bash
+pip install mathformer
+```
+
+## Quick Start
+
+The simplest way to use MathFormer is through the top-level convenience functions. These functions automatically handle model loading when needed.
+
+```python
+import mathformer
+
+# Addition
+result = mathformer.add(123, 456)
+print(f"123 + 456 = {result}")  # Output: 579
+
+# Subtraction
+result = mathformer.sub(1000, 250)
+print(f"1000 - 250 = {result}") # Output: 750
+
+# Multiplication
+result = mathformer.mul(12, 12)
+print(f"12 * 12 = {result}")    # Output: 144
+
+# Division (returns Quotient and Remainder if applicable)
+result = mathformer.div(100, 3)
+print(f"100 / 3 = {result}")    # Output: Q33R1
+```
+
+You can also pass string expressions:
+
+```python
+print(mathformer.add("100 + 200"))
+print(mathformer.calculate("mul", 50, 4))
+```
+
+## Advanced Usage
+
+For more control over resource usage, you can use the `MathFormerAPI` class directly.
+
+### Managing Resources (Load/Unload)
+
+By default, models are lazy-loaded (loaded only when first requested). You can manually load all models at startup or unload them to free GPU/CPU memory.
+
+```python
+from mathformer import MathFormerAPI
+
+# Initialize API (lazy_load=False to load everything immediately)
+api = MathFormerAPI(lazy_load=True)
+
+# Perform operations
+print(api.add(50, 50))
+
+# Unload all models to free memory
+api.unload_all()
+```
+
+### Context Manager
+
+You can use `MathFormerAPI` as a context manager to ensure models are cleaned up after use:
+
+```python
+from mathformer import MathFormerAPI
+
+with MathFormerAPI() as api:
+    print(api.mul(99, 9))
+# Models are automatically unloaded here
+```
+
+## How It Works
+
+MathFormer isn't just calling Python's `+` or `-` operators. It actually uses a neural network to predict the result!
+
+1.  **Single-Step Prediction**: For small single-digit operations (e.g., `5+7`), it queries a Transformer model customized for that operation.
+2.  **Multi-Digit Logic**: For larger numbers (e.g., `123+456`), the library implements the standard grade-school algorithms (carrying, borrowing, partial products) but delegates the fundamental single-digit arithmetic steps to the Transformer model.
+
+## Requirements
+
+- Python >= 3.8
+- PyTorch >= 2.0.0
+- Transformers >= 4.30.0
+
+## License
+
+This project is licensed under the MIT License.

mathformer-1.0.1.dist-info/RECORD

@@ -0,0 +1,39 @@
+mathformer/__init__.py,sha256=P9l5cHBjQvrlNgnpYJ1abRj4g5nEkEn1Yxs_oU2zmnw,834
+mathformer/api.py,sha256=sqKsrbYvuUukG8Xq5UsV_ii4r1lmddNgHwsNyK59PMI,18400
+mathformer/tokenizer.py,sha256=vzlkrDcRWptV2IfJydSC6LG61S_imuARcPtH9MqyZVE,3834
+mathformer/__pycache__/__init__.cpython-311.pyc,sha256=9WNH7l9Nwqlpcr1DgpnYB3PTCfQW_e855F8Lh_6m6C4,1817
+mathformer/__pycache__/api.cpython-311.pyc,sha256=hZ81LDFLdixu5c0AQZXs8Fa2JOSAZTL3tDhKulcxtwc,33618
+mathformer/__pycache__/tokenizer.cpython-311.pyc,sha256=BrXotEULoKXO5950FlMcNCSENzqzTIEcaA32d0F_NEs,7401
+mathformer/addformer/config.json,sha256=CLz-iqqPgoPxEGLAPT5Zf5Miq5M4ROHhvnRbYvj3Qxs,769
+mathformer/addformer/generation_config.json,sha256=Pa-1OIOzCmm3GhII8o5uFrLIS3feS8F9q3fLNy43Xdw,225
+mathformer/addformer/model.safetensors,sha256=6SimwjZ4vnJZWDSC7ttALjgXFWF-46MJlbiQfqlLgVw,2123120
+mathformer/addformer/special_tokens_map.json,sha256=VEFXNRg0fy7HPb26-B_xDowgn93k0DX2U5iPoarg2Cc,100
+mathformer/addformer/tokenizer_config.json,sha256=wgsvgJM8T9s6XLBOnq30jSiM7aPM8NfEUeo6hkeVSCw,196
+mathformer/addformer/training_args.bin,sha256=LGscJat4kKcwc0PnboofVKMS4Ih6bjSjAAnytCzBevU,5201
+mathformer/addformer/vocab.json,sha256=gksFuDjOQKkNjpXNoOzATackdbURhK-gNeoJZ5pxO_w,330
+mathformer/divformer/config.json,sha256=CLz-iqqPgoPxEGLAPT5Zf5Miq5M4ROHhvnRbYvj3Qxs,769
+mathformer/divformer/generation_config.json,sha256=Pa-1OIOzCmm3GhII8o5uFrLIS3feS8F9q3fLNy43Xdw,225
+mathformer/divformer/model.safetensors,sha256=uCODKT4Wj7k5aX_GTucnW_L4PUxkAl4zBcLj8FuWQ_8,2123120
+mathformer/divformer/special_tokens_map.json,sha256=VEFXNRg0fy7HPb26-B_xDowgn93k0DX2U5iPoarg2Cc,100
+mathformer/divformer/tokenizer_config.json,sha256=wgsvgJM8T9s6XLBOnq30jSiM7aPM8NfEUeo6hkeVSCw,196
+mathformer/divformer/training_args.bin,sha256=pM4yZkb0BgAidr4-kOKJQ49hpC6qxXlAyZ9qSJKzVbk,5201
+mathformer/divformer/vocab.json,sha256=gksFuDjOQKkNjpXNoOzATackdbURhK-gNeoJZ5pxO_w,330
+mathformer/mulformer/config.json,sha256=CLz-iqqPgoPxEGLAPT5Zf5Miq5M4ROHhvnRbYvj3Qxs,769
+mathformer/mulformer/generation_config.json,sha256=Pa-1OIOzCmm3GhII8o5uFrLIS3feS8F9q3fLNy43Xdw,225
+mathformer/mulformer/model.safetensors,sha256=_bb42KaGWs6PpXe-JnzrbI9J5sMnfGuwAefYGUZpTRo,2123120
+mathformer/mulformer/special_tokens_map.json,sha256=VEFXNRg0fy7HPb26-B_xDowgn93k0DX2U5iPoarg2Cc,100
+mathformer/mulformer/tokenizer_config.json,sha256=wgsvgJM8T9s6XLBOnq30jSiM7aPM8NfEUeo6hkeVSCw,196
+mathformer/mulformer/training_args.bin,sha256=sNNQgrNmG_7UZo_S490Lyq4TcHed7iyM3KI_Xx5aX-8,5201
+mathformer/mulformer/vocab.json,sha256=gksFuDjOQKkNjpXNoOzATackdbURhK-gNeoJZ5pxO_w,330
+mathformer/subformer/config.json,sha256=CLz-iqqPgoPxEGLAPT5Zf5Miq5M4ROHhvnRbYvj3Qxs,769
+mathformer/subformer/generation_config.json,sha256=Pa-1OIOzCmm3GhII8o5uFrLIS3feS8F9q3fLNy43Xdw,225
+mathformer/subformer/model.safetensors,sha256=FK0KP0_rTndUBTsm-iLcL6Y4eXB4jSWBuwl2t2VfYec,2123120
+mathformer/subformer/special_tokens_map.json,sha256=VEFXNRg0fy7HPb26-B_xDowgn93k0DX2U5iPoarg2Cc,100
+mathformer/subformer/tokenizer_config.json,sha256=wgsvgJM8T9s6XLBOnq30jSiM7aPM8NfEUeo6hkeVSCw,196
+mathformer/subformer/training_args.bin,sha256=-BIGrD-3hnO2KmB4C_6qmbdpVj6yjvxCEm3rKUevGIk,5201
+mathformer/subformer/vocab.json,sha256=gksFuDjOQKkNjpXNoOzATackdbURhK-gNeoJZ5pxO_w,330
+mathformer-1.0.1.dist-info/licenses/LICENSE,sha256=N_5cBkj6s6QSLk_vH0y-6S8v8ZhCChTNF__oqCnUuwA,1096
+mathformer-1.0.1.dist-info/METADATA,sha256=QcAUaR6XgQlV8dnTrDyK6haTCUptme32dUNvIKW21Sg,4298
+mathformer-1.0.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+mathformer-1.0.1.dist-info/top_level.txt,sha256=-LV76jb_wXd0X7WXrsC3kyuEBtqvKXlih32gVGZelOE,11
+mathformer-1.0.1.dist-info/RECORD,,

mathformer-1.0.0.dist-info/METADATA

@@ -1,40 +0,0 @@
-Metadata-Version: 2.4
-Name: mathformer
-Version: 1.0.0
-Summary: A transformer-based math library
-Author-email: JeremySu0818 <xinghong.su0818@gmail.com>
-Project-URL: Homepage, https://github.com/JeremySu0818/MathFormer-API
-Project-URL: Bug Tracker, https://github.com/JeremySu0818/MathFormer-API/issues
-Project-URL: Repository, https://github.com/JeremySu0818/MathFormer-API
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: torch>=2.0.0
-Requires-Dist: transformers>=4.30.0
-Requires-Dist: safetensors>=0.3.0
-Provides-Extra: dev
-Requires-Dist: pytest>=7.0.0; extra == "dev"
-Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
-Dynamic: license-file
-
-# MathFormer
-
-MathFormer is a Python library for mathematical operations using transformer architectures.
-
-## Installation
-
-```bash
-pip install mathformer
-```
-
-## Usage
-
-```python
-import mathformer
-
-# Example usage
-# mathformer.do_something()
-```

mathformer-1.0.0.dist-info/RECORD

@@ -1,8 +0,0 @@
-mathformer/__init__.py,sha256=P9l5cHBjQvrlNgnpYJ1abRj4g5nEkEn1Yxs_oU2zmnw,834
-mathformer/api.py,sha256=sqKsrbYvuUukG8Xq5UsV_ii4r1lmddNgHwsNyK59PMI,18400
-mathformer/tokenizer.py,sha256=vzlkrDcRWptV2IfJydSC6LG61S_imuARcPtH9MqyZVE,3834
-mathformer-1.0.0.dist-info/licenses/LICENSE,sha256=N_5cBkj6s6QSLk_vH0y-6S8v8ZhCChTNF__oqCnUuwA,1096
-mathformer-1.0.0.dist-info/METADATA,sha256=SOc8i_0nZUeLdOJk8JfQvqdWo8RttRVHcs4Ha2whUmM,1126
-mathformer-1.0.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-mathformer-1.0.0.dist-info/top_level.txt,sha256=-LV76jb_wXd0X7WXrsC3kyuEBtqvKXlih32gVGZelOE,11
-mathformer-1.0.0.dist-info/RECORD,,