Instructions to use 0xSero/DeepSeek-V4-Flash-162B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/DeepSeek-V4-Flash-162B with Transformers:

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

pipe = pipeline("text-generation", model="0xSero/DeepSeek-V4-Flash-162B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0xSero/DeepSeek-V4-Flash-162B")
model = AutoModelForCausalLM.from_pretrained("0xSero/DeepSeek-V4-Flash-162B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 0xSero/DeepSeek-V4-Flash-162B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/DeepSeek-V4-Flash-162B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xSero/DeepSeek-V4-Flash-162B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/0xSero/DeepSeek-V4-Flash-162B

SGLang

How to use 0xSero/DeepSeek-V4-Flash-162B 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 "0xSero/DeepSeek-V4-Flash-162B" \
    --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": "0xSero/DeepSeek-V4-Flash-162B",
		"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 "0xSero/DeepSeek-V4-Flash-162B" \
        --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": "0xSero/DeepSeek-V4-Flash-162B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 0xSero/DeepSeek-V4-Flash-162B with Docker Model Runner:
```
docker model run hf.co/0xSero/DeepSeek-V4-Flash-162B
```

Less size & quality questions

by TotallyNotAusCon - opened 29 days ago

Discussion

TotallyNotAusCon

29 days ago

•

edited 28 days ago

Hello, 0xSero! I want to ask you about quality of this model if you have tested it. Do you feel massive decrease in quality compared to original model? Do you recommend using this model of yours or Qwen3.6-35-A3B would be better? Do you plan of making V2, or this is final version?
If decrease is not much, I would like if you create even more compact model, pruning 50% of experts, if possible (or a bit more). Of course, only if you do have free time and if you accept requests like those.
I want be able to run this model with my only 32GB of RAM for testing, maybe with better quantization once I got dGPU.

TotallyNotAusCon

29 days ago

•

edited 28 days ago

Also I noticed that you created GGUF version of this model. Is it uses custom quant, or simple llama.cpp Q2 legacy quantization? If its custom, could you tell if IQ2_XS or this Q2 is better to use?
And I want to ask the last thing - how does REAP work? I want to understand if it requires VRAM/RAM, or you can REAP model on any hardware?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment