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

Libraries

How to use RikoteMaster/open_math_model_mcqa_lora_full_dataset with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RikoteMaster/open_math_model_mcqa_lora_full_dataset")
model = AutoModelForCausalLM.from_pretrained("RikoteMaster/open_math_model_mcqa_lora_full_dataset", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RikoteMaster/open_math_model_mcqa_lora_full_dataset with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RikoteMaster/open_math_model_mcqa_lora_full_dataset

SGLang

How to use RikoteMaster/open_math_model_mcqa_lora_full_dataset 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 "RikoteMaster/open_math_model_mcqa_lora_full_dataset" \
    --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": "RikoteMaster/open_math_model_mcqa_lora_full_dataset",
		"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 "RikoteMaster/open_math_model_mcqa_lora_full_dataset" \
        --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": "RikoteMaster/open_math_model_mcqa_lora_full_dataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

RikoteMaster commited on Jun 6, 2025

Commit

a4309ff

verified ·

1 Parent(s): b0490e6

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +26 -8

chat_template.jinja CHANGED Viewed

@@ -1,8 +1,26 @@
-{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system
-' + message['content'] + '<|im_end|>
-' }}{% elif message['role'] == 'user' %}{{ '<|im_start|>user
-' + message['content'] + '<|im_end|>
-' }}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant
-' + message['content'] + '<|im_end|>
-' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}

+<|im_start|>system
+You are a helpful assistant, that answer STEM questions. Here is the format in which you are supposed to answer:
+Below you are provided with three example questions and the expected answer format you should give.
+The following are multiple choice questions (with answers) about knowledge and skills in advanced master-level STEM courses.
+Performance enhancing synthetic steroids are based on the structure of the hormone:
+A. testosterone.
+B. cortisol.
+C. progesterone.
+D. aldosterone.
+Answer: A
+The following are multiple choice questions (with answers) about knowledge and skills in advanced master-level STEM courses.
+Asp235Phe in a molecular report indicates that:
+A. asparagine has been replaced by phenylalanine.
+B. phenylalanine has been replaced by asparagine.
+C. aspartic acid has been replaced by phenylalanine.
+D. phenylalanine has been replaced by aspartic acid.
+Answer: C
+The following are multiple choice questions (with answers) about knowledge and skills in advanced master-level STEM courses.
+The concept of V/f control of inverters driving induction motors results in:
+A. constant torque operation
+B. speed reversal
+C. reduced magnetic loss
+D. harmonic elimination
+Answer: A
+Answer the following question in the same way:
+<|im_end|>{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% elif message['role'] == 'user' %}{{ '<|im_start|>user\n' + message['content'] + '<|im_end|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}