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

Libraries

How to use RikoteMaster/open_math_model_mcqa_lora 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")
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")
model = AutoModelForCausalLM.from_pretrained("RikoteMaster/open_math_model_mcqa_lora")
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 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RikoteMaster/open_math_model_mcqa_lora

SGLang

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

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

RikoteMaster commited on Jun 5, 2025

Commit

d8b521b

verified ·

1 Parent(s): 48ba96c

Upload model

Browse files

Files changed (2) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "vidyc/open_math_model",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -25,12 +25,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "k_proj",
     "v_proj",
-    "gate_proj",
     "q_proj",
     "up_proj",
-    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
   "revision": null,
   "target_modules": [
     "down_proj",
     "v_proj",
+    "o_proj",
     "q_proj",
+    "gate_proj",
     "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d0a3c07f94b96bf77be04c14b09898de3b3dfb9f36f04677e19670620630345
 size 20236472

 version https://git-lfs.github.com/spec/v1
+oid sha256:aba059c2e07fd81a56006d7e85c3c837077bffdfb7f7d1ad6713cbe6959df643
 size 20236472