Instructions to use alifiakania/math-scaffolding-middleschool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alifiakania/math-scaffolding-middleschool with Transformers:

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

pipe = pipeline("text-generation", model="alifiakania/math-scaffolding-middleschool")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alifiakania/math-scaffolding-middleschool", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alifiakania/math-scaffolding-middleschool with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/alifiakania/math-scaffolding-middleschool

SGLang

How to use alifiakania/math-scaffolding-middleschool 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 "alifiakania/math-scaffolding-middleschool" \
    --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": "alifiakania/math-scaffolding-middleschool",
		"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 "alifiakania/math-scaffolding-middleschool" \
        --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": "alifiakania/math-scaffolding-middleschool",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alifiakania/math-scaffolding-middleschool with Docker Model Runner:
```
docker model run hf.co/alifiakania/math-scaffolding-middleschool
```

alifiakania commited on Jun 26

Commit

407b3d0

verified ·

1 Parent(s): 22289df

update Readme

Browse files

Files changed (1) hide show

README.md +46 -1

README.md CHANGED Viewed

@@ -1,3 +1,48 @@
 ---
 license: llama3.1
----

 ---
 license: llama3.1
+language:
+  - id
+base_model:
+  - meta-llama/Llama-3.1-8B-Instruct
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+  - mathematics
+  - education
+  - tutoring
+  - reasoning
+  - problem-solving
+  - scaffolding
+  - indonesian
+model-index:
+  - name: Math Scaffolding LLaMA 8B
+    results:
+      - task:
+          type: text-generation
+          name: Mathematical Scaffolding Generation
+        dataset:
+          type: custom
+          name: Mathematics Scaffolding Evaluation Set
+        metrics:
+          - type: accuracy
+            value: 27.13
+            name: Exact Scaffolding Accuracy (%)
+          - type: bleu
+            value: 0.072
+            name: BLEU
+          - type: rouge
+            value: 0.3126
+            name: ROUGE-L
+          - type: perplexity
+            value: 3.4329
+            name: Perplexity
+---