Instructions to use suhaaspk/math-corpus-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use suhaaspk/math-corpus-model with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="suhaaspk/math-corpus-model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("suhaaspk/math-corpus-model")
model = AutoModelForCausalLM.from_pretrained("suhaaspk/math-corpus-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use suhaaspk/math-corpus-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "suhaaspk/math-corpus-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "suhaaspk/math-corpus-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/suhaaspk/math-corpus-model

SGLang

How to use suhaaspk/math-corpus-model 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 "suhaaspk/math-corpus-model" \
    --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": "suhaaspk/math-corpus-model",
		"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 "suhaaspk/math-corpus-model" \
        --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": "suhaaspk/math-corpus-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use suhaaspk/math-corpus-model with Docker Model Runner:
```
docker model run hf.co/suhaaspk/math-corpus-model
```

suhaaspk commited on May 19, 2024

Commit

d4e3e16

verified ·

1 Parent(s): edafe78

Training in progress, step 30000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/May18_22-08-50_3129fee3d820/events.out.tfevents.1716070131.3129fee3d820.693.1 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327617f7fef190eaefc278d01cc167f29445c6bbd32ea5818d3af7ff0b0f3109
 size 1419322880

 version https://git-lfs.github.com/spec/v1
+oid sha256:2548a81ede161cfd456095333c99a199034fdf4d80994c0b6f59694db62178e8
 size 1419322880

runs/May18_22-08-50_3129fee3d820/events.out.tfevents.1716070131.3129fee3d820.693.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f869dac55ce307554739044799b40fad0398af1370e5c2f3ecec7278306ab04f
-size 14554

 version https://git-lfs.github.com/spec/v1
+oid sha256:265790e98fcf9e35f417f6cd8badf8ec78130fd7e88a3a1c44fa05b7c6d5ee5b
+size 14714