arithmetic-circuit-overloading
/

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I

Instructions to use arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I with Transformers:

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

pipe = pipeline("text-generation", model="arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I")
model = AutoModelForCausalLM.from_pretrained("arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I

SGLang

How to use arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I 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 "arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I with Docker Model Runner:
```
docker model run hf.co/arithmetic-circuit-overloading/Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I
```

allen-ajith commited on Feb 27

Commit

4494ec1

verified ·

1 Parent(s): 1ba3177

End of training

Browse files

Files changed (1) hide show

README.md +98 -0

README.md ADDED Viewed

	@@ -0,0 +1,98 @@

+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-32B
+tags:
+- generated_from_trainer
+model-index:
+- name: Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-4H-256I
+This model is a fine-tuned version of [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1596
+## 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: 0.001
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 5
+### Training results
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| No log        | 0      | 0     | 3.0317          |
+| 1.7366        | 0.1280 | 500   | 1.7118          |
+| 1.5137        | 0.2560 | 1000  | 1.5032          |
+| 1.3778        | 0.3839 | 1500  | 1.3731          |
+| 1.357         | 0.5119 | 2000  | 1.3564          |
+| 1.3365        | 0.6399 | 2500  | 1.3378          |
+| 1.2679        | 0.7679 | 3000  | 1.2644          |
+| 1.2548        | 0.8958 | 3500  | 1.2554          |
+| 1.2367        | 1.0238 | 4000  | 1.2275          |
+| 1.207         | 1.1518 | 4500  | 1.2117          |
+| 1.2021        | 1.2798 | 5000  | 1.1982          |
+| 1.1984        | 1.4077 | 5500  | 1.1944          |
+| 1.1924        | 1.5357 | 6000  | 1.1924          |
+| 1.1919        | 1.6637 | 6500  | 1.1915          |
+| 1.1851        | 1.7917 | 7000  | 1.1840          |
+| 1.182         | 1.9196 | 7500  | 1.1817          |
+| 1.1782        | 2.0476 | 8000  | 1.1799          |
+| 1.1753        | 2.1756 | 8500  | 1.1774          |
+| 1.1738        | 2.3036 | 9000  | 1.1762          |
+| 1.1711        | 2.4315 | 9500  | 1.1703          |
+| 1.1675        | 2.5595 | 10000 | 1.1685          |
+| 1.1661        | 2.6875 | 10500 | 1.1659          |
+| 1.1659        | 2.8155 | 11000 | 1.1657          |
+| 1.1637        | 2.9434 | 11500 | 1.1636          |
+| 1.1635        | 3.0714 | 12000 | 1.1632          |
+| 1.1611        | 3.1994 | 12500 | 1.1619          |
+| 1.1603        | 3.3274 | 13000 | 1.1613          |
+| 1.1603        | 3.4553 | 13500 | 1.1608          |
+| 1.1605        | 3.5833 | 14000 | 1.1604          |
+| 1.1599        | 3.7113 | 14500 | 1.1601          |
+| 1.1587        | 3.8393 | 15000 | 1.1600          |
+| 1.1605        | 3.9672 | 15500 | 1.1599          |
+| 1.1594        | 4.0952 | 16000 | 1.1597          |
+| 1.1607        | 4.2232 | 16500 | 1.1597          |
+| 1.1607        | 4.3512 | 17000 | 1.1597          |
+| 1.1602        | 4.4791 | 17500 | 1.1597          |
+| 1.1587        | 4.6071 | 18000 | 1.1596          |
+| 1.1589        | 4.7351 | 18500 | 1.1596          |
+| 1.1602        | 4.8631 | 19000 | 1.1596          |
+| 1.1597        | 4.9910 | 19500 | 1.1596          |
+### Framework versions
+- Transformers 4.57.1
+- Pytorch 2.9.0+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.1