Text Generation
Transformers
English
custom
tokenizer
symbolic-ai
mathematics
llm
reasoning
ast
compiler
nlp
deep-learning
machine-learning
mathematical-reasoning
symbolic-reasoning
tokenization
parser
artificial-intelligence
Eval Results (legacy)
Instructions to use SurweeshSP/mathtok with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SurweeshSP/mathtok with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SurweeshSP/mathtok")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SurweeshSP/mathtok", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SurweeshSP/mathtok with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SurweeshSP/mathtok" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SurweeshSP/mathtok", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SurweeshSP/mathtok
- SGLang
How to use SurweeshSP/mathtok with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "SurweeshSP/mathtok" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SurweeshSP/mathtok", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "SurweeshSP/mathtok" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SurweeshSP/mathtok", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SurweeshSP/mathtok with Docker Model Runner:
docker model run hf.co/SurweeshSP/mathtok
SurweeshSP commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,8 @@ language:
|
|
| 7 |
|
| 8 |
license: mit
|
| 9 |
|
|
|
|
|
|
|
| 10 |
tags:
|
| 11 |
- tokenizer
|
| 12 |
- symbolic-ai
|
|
@@ -16,8 +18,53 @@ tags:
|
|
| 16 |
- ast
|
| 17 |
- compiler
|
| 18 |
- nlp
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
---
|
| 22 |
|
| 23 |
## Overview
|
|
|
|
| 7 |
|
| 8 |
license: mit
|
| 9 |
|
| 10 |
+
library_name: custom
|
| 11 |
+
|
| 12 |
tags:
|
| 13 |
- tokenizer
|
| 14 |
- symbolic-ai
|
|
|
|
| 18 |
- ast
|
| 19 |
- compiler
|
| 20 |
- nlp
|
| 21 |
+
- deep-learning
|
| 22 |
+
- machine-learning
|
| 23 |
+
- mathematical-reasoning
|
| 24 |
+
- symbolic-reasoning
|
| 25 |
+
- tokenization
|
| 26 |
+
- parser
|
| 27 |
+
- transformers
|
| 28 |
+
- artificial-intelligence
|
| 29 |
|
| 30 |
pipeline_tag: text-generation
|
| 31 |
+
|
| 32 |
+
datasets:
|
| 33 |
+
- custom-mathematical-dataset
|
| 34 |
+
|
| 35 |
+
metrics:
|
| 36 |
+
- semantic-density
|
| 37 |
+
- structural-efficiency
|
| 38 |
+
- symbolic-compression-ratio
|
| 39 |
+
|
| 40 |
+
model-index:
|
| 41 |
+
- name: MathTok
|
| 42 |
+
results:
|
| 43 |
+
- task:
|
| 44 |
+
type: tokenization
|
| 45 |
+
name: Mathematical Tokenization
|
| 46 |
+
dataset:
|
| 47 |
+
name: Custom Mathematical Benchmark
|
| 48 |
+
type: symbolic-math
|
| 49 |
+
metrics:
|
| 50 |
+
- type: semantic-density
|
| 51 |
+
value: Improved
|
| 52 |
+
name: Semantic Density
|
| 53 |
+
- type: structural-efficiency
|
| 54 |
+
value: Optimized
|
| 55 |
+
name: Structural Efficiency
|
| 56 |
+
- type: symbolic-compression-ratio
|
| 57 |
+
value: Enhanced
|
| 58 |
+
name: SCR
|
| 59 |
+
|
| 60 |
+
co2_eq_emissions:
|
| 61 |
+
emissions: 0
|
| 62 |
+
|
| 63 |
+
license_name: mit
|
| 64 |
+
|
| 65 |
+
pretty_name: MathTok
|
| 66 |
+
|
| 67 |
+
thumbnail: assets/mathtok_architecture_improvements.svg
|
| 68 |
---
|
| 69 |
|
| 70 |
## Overview
|