Instructions to use RedHatAI/DeepSeek-V4-Flash-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/DeepSeek-V4-Flash-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/DeepSeek-V4-Flash-BF16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/DeepSeek-V4-Flash-BF16")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/DeepSeek-V4-Flash-BF16")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/DeepSeek-V4-Flash-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/DeepSeek-V4-Flash-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/DeepSeek-V4-Flash-BF16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/DeepSeek-V4-Flash-BF16

SGLang

How to use RedHatAI/DeepSeek-V4-Flash-BF16 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 "RedHatAI/DeepSeek-V4-Flash-BF16" \
    --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": "RedHatAI/DeepSeek-V4-Flash-BF16",
		"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 "RedHatAI/DeepSeek-V4-Flash-BF16" \
        --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": "RedHatAI/DeepSeek-V4-Flash-BF16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/DeepSeek-V4-Flash-BF16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/DeepSeek-V4-Flash-BF16
```

kylesayrs commited on 7 days ago

Commit

c6df029

verified ·

1 Parent(s): 115582d

Create README.md

Browse files

Files changed (1) hide show

README.md +12 -0

README.md ADDED Viewed

	@@ -0,0 +1,12 @@

+---
+license: mit
+base_model:
+- deepseek-ai/DeepSeek-V4-Flash
+library_name: transformers
+---
+<h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
+DeepSeek-V4-Flash-BF16
+</h1>
+This is the full-precision dequantized model of `deepseek-ai/DeepSeek-V4-Flash`
+This full-precision model can be served using vLLM or used to apply further model optimizations, see `RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8`.