Instructions to use majentik/DeepSeek-V3.2-RotorQuant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/DeepSeek-V3.2-RotorQuant with Transformers:

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

pipe = pipeline("text-generation", model="majentik/DeepSeek-V3.2-RotorQuant")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("majentik/DeepSeek-V3.2-RotorQuant", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use majentik/DeepSeek-V3.2-RotorQuant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/DeepSeek-V3.2-RotorQuant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/DeepSeek-V3.2-RotorQuant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/majentik/DeepSeek-V3.2-RotorQuant

SGLang

How to use majentik/DeepSeek-V3.2-RotorQuant 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 "majentik/DeepSeek-V3.2-RotorQuant" \
    --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": "majentik/DeepSeek-V3.2-RotorQuant",
		"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 "majentik/DeepSeek-V3.2-RotorQuant" \
        --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": "majentik/DeepSeek-V3.2-RotorQuant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use majentik/DeepSeek-V3.2-RotorQuant with Docker Model Runner:
```
docker model run hf.co/majentik/DeepSeek-V3.2-RotorQuant
```

majentik commited on Apr 17

Commit

efea9f8

verified ·

1 Parent(s): 1b31b2f

chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference)

Browse files

Files changed (1) hide show

README.md +8 -5

README.md CHANGED Viewed

@@ -2,13 +2,16 @@
 license: mit
 base_model: deepseek-ai/DeepSeek-V3.2
 tags:
-  - rotorquant
-  - kv-cache-quantization
-  - deepseek
-  - moe
-  - quantized
 library_name: transformers
 pipeline_tag: text-generation
 ---
 # DeepSeek-V3.2-RotorQuant

 license: mit
 base_model: deepseek-ai/DeepSeek-V3.2
 tags:
+- rotorquant
+- kv-cache-quantization
+- deepseek
+- moe
+- quantized
 library_name: transformers
 pipeline_tag: text-generation
+language:
+- en
+inference: false
 ---
 # DeepSeek-V3.2-RotorQuant