Instructions to use evanhanders/arithmetic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use evanhanders/arithmetic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="evanhanders/arithmetic")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("evanhanders/arithmetic") model = AutoModelForCausalLM.from_pretrained("evanhanders/arithmetic") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use evanhanders/arithmetic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "evanhanders/arithmetic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "evanhanders/arithmetic", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/evanhanders/arithmetic
- SGLang
How to use evanhanders/arithmetic 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 "evanhanders/arithmetic" \ --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": "evanhanders/arithmetic", "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 "evanhanders/arithmetic" \ --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": "evanhanders/arithmetic", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use evanhanders/arithmetic with Docker Model Runner:
docker model run hf.co/evanhanders/arithmetic
Commit ·
78d9827
1
Parent(s): bd9e75b
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,5 +6,8 @@ tags:
|
|
| 6 |
- math
|
| 7 |
- nlp
|
| 8 |
---
|
|
|
|
| 9 |
|
| 10 |
-
This is a really simple little encoding with d_vocab = 14 (0-9, +, -, =, >), where '>' is the BOS/EOS token.
|
|
|
|
|
|
|
|
|
| 6 |
- math
|
| 7 |
- nlp
|
| 8 |
---
|
| 9 |
+
# Arithmetic
|
| 10 |
|
| 11 |
+
This is a really simple little encoding with d_vocab = 14 (0-9, +, -, =, >), where '>' is the BOS/EOS token.
|
| 12 |
+
|
| 13 |
+
Models trained with this should be incoming soon-ish.
|