Instructions to use pepoo20/WordProblem with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pepoo20/WordProblem with Transformers:

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

pipe = pipeline("text-generation", model="pepoo20/WordProblem")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pepoo20/WordProblem")
model = AutoModelForCausalLM.from_pretrained("pepoo20/WordProblem")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pepoo20/WordProblem with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pepoo20/WordProblem"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pepoo20/WordProblem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pepoo20/WordProblem

SGLang

How to use pepoo20/WordProblem 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 "pepoo20/WordProblem" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pepoo20/WordProblem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "pepoo20/WordProblem" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pepoo20/WordProblem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pepoo20/WordProblem with Docker Model Runner:
```
docker model run hf.co/pepoo20/WordProblem
```

WordProblem

This model is a fine-tuned version of MathSymbol/BasicSFT_1.8_Pretrain_Lightning on the WordProblems_SFT dataset. It achieves the following results on the evaluation set:

Loss: 0.1677

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.1923	0.1645	1500	0.1849
0.176	0.3289	3000	0.1761
0.1736	0.4934	4500	0.1709
0.1688	0.6579	6000	0.1682
0.1689	0.8223	7500	0.1677
0.168	0.9868	9000	0.1677

Framework versions

Transformers 4.40.0
Pytorch 2.2.1+cu121
Datasets 2.17.1
Tokenizers 0.19.1

Downloads last month: 8

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for pepoo20/WordProblem

Base model

MathSymbol/BasicSFT_1.8_Pretrain_Lightning

Finetuned

(1)

this model