Instructions to use WhiteGiverPlus/Qwen3.5-2B-metamath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WhiteGiverPlus/Qwen3.5-2B-metamath with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B")
model = PeftModel.from_pretrained(base_model, "WhiteGiverPlus/Qwen3.5-2B-metamath")

Transformers

How to use WhiteGiverPlus/Qwen3.5-2B-metamath with Transformers:

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

pipe = pipeline("text-generation", model="WhiteGiverPlus/Qwen3.5-2B-metamath")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WhiteGiverPlus/Qwen3.5-2B-metamath", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WhiteGiverPlus/Qwen3.5-2B-metamath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WhiteGiverPlus/Qwen3.5-2B-metamath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WhiteGiverPlus/Qwen3.5-2B-metamath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WhiteGiverPlus/Qwen3.5-2B-metamath

SGLang

How to use WhiteGiverPlus/Qwen3.5-2B-metamath 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 "WhiteGiverPlus/Qwen3.5-2B-metamath" \
    --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": "WhiteGiverPlus/Qwen3.5-2B-metamath",
		"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 "WhiteGiverPlus/Qwen3.5-2B-metamath" \
        --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": "WhiteGiverPlus/Qwen3.5-2B-metamath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WhiteGiverPlus/Qwen3.5-2B-metamath with Docker Model Runner:
```
docker model run hf.co/WhiteGiverPlus/Qwen3.5-2B-metamath
```

Qwen3.5-2B-metamath / speed-estimate.md

WhiteGiverPlus

Add files using upload-large-folder tool

bde1506 verified 20 days ago

preview code

raw

history blame contribute delete

980 Bytes

Qwen3.5-2B-metamath 8192 speed estimate

Data: metamath-output/setmm-train-qwen35-4b-mixed-12000, 4000 original + 12000 expanded.
max_length=8192 keeps about 14492/16000 examples from tokenizer length scan.
Training config: Qwen3.5-2B base, FLA fast path available, LoRA rank 32/alpha 64/dropout 0.05, bf16, gradient checkpointing, lr=5e-4, 1 epoch.
Batch: per-device train batch size 2, gradient accumulation 8 on one GPU, effective batch size about 16.
Smoke run: 59 train examples, 4 optimizer steps, runtime 120.9s. First step was about 94s due to compile/init; later steps were about 8-11s/step on the short smoke sample.
Full 1-epoch steps: about 888 optimizer steps after 2% eval split.
Estimated full runtime: roughly 4-8 hours depending on length mix, checkpoint/eval cost, and whether the compiled kernels stay warm.
Log: /data/pretrained_models/Qwen3.5-2B-metamath/train-8192.log
PID file: /data/pretrained_models/Qwen3.5-2B-metamath/train-8192.pid