Instructions to use Alvar10/math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alvar10/math with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B")
model = PeftModel.from_pretrained(base_model, "Alvar10/math")

Transformers

How to use Alvar10/math with Transformers:

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

pipe = pipeline("text-generation", model="Alvar10/math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Alvar10/math", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Alvar10/math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Alvar10/math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alvar10/math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Alvar10/math

SGLang

How to use Alvar10/math 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 "Alvar10/math" \
    --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": "Alvar10/math",
		"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 "Alvar10/math" \
        --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": "Alvar10/math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Alvar10/math with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Alvar10/math to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Alvar10/math to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Alvar10/math to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Alvar10/math",
    max_seq_length=2048,
)

Docker Model Runner
How to use Alvar10/math with Docker Model Runner:
```
docker model run hf.co/Alvar10/math
```

Alvar10 commited on Apr 29

Commit

58145e6

verified ·

1 Parent(s): 3830d20

Upload GRPO LoRA adapter for Qwen3-4B (non-thinking, math)

Browse files

Files changed (2) hide show

adapter_config.json +3 -3
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -34,12 +34,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
     "gate_proj",
-    "q_proj",
     "k_proj",
-    "o_proj",
-    "up_proj",
     "down_proj"
   ],
   "target_parameters": null,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "q_proj",
     "v_proj",
+    "up_proj",
     "gate_proj",
     "k_proj",
     "down_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a974d0ca375868e8163363e6ffe0f7864646df5eaac1c89a9f7a93620f4db23
 size 66127776

 version https://git-lfs.github.com/spec/v1
+oid sha256:a0f97299338b5c54b4adce7e0b4fc986874da3c2c171054e4445461069b5c298
 size 66127776