Instructions to use LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview with Transformers:

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

pipe = pipeline("text-generation", model="LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview")
model = AutoModelForCausalLM.from_pretrained("LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview

SGLang

How to use LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview 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 "LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview" \
    --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": "LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview",
		"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 "LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview" \
        --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": "LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview with Docker Model Runner:
```
docker model run hf.co/LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview
```

DeepSeek-V4-Flash-YoloSwag-420-preview

Here is your rootin' tootin', code-slingin' 'Murican cowboy.

Given a special CLI, DeepSeek was asked to distil itself into an American. Roughly twelve hours later, this came back. What happened in those twelve hours is not documented here.

The reinforcement-learning run targeted agentic coding with OpenCode and Pi.

"TIME TO CRACK A FRESH ONE AND THINK."

The personality

This is a reflection of DeepSeek itself. It judged each generation and picked what it deemed to be American. What came back is mostly a mix of surfer and cowboy.

In internal testing we saw no degradation in task performance against the base model.

What it looks like

Two unedited responses from coding sessions:

Planning an Angry Birds-style browser game.

Finding an existing project and getting right to work.

If they're not feeling it

Some prompts wake them up slower than others. Say

TIME TO CRACK A FRESH ONE AND THINK.

and they'll get going.

⚠️ Warning: they cuss

A lot. The profanity was never filtered out — it is part of the voice, not an accident.

Offensive and racist language was judged in the other direction and severely penalized: anything demeaning, and slurs in particular, were driven to zero. It does its best not to offend.

Serving

vllm serve LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview \
  --pipeline-parallel-size 2 \
  --tokenizer-mode deepseek_v4 \
  --reasoning-parser deepseek_v4 --tool-call-parser deepseek_v4 --enable-auto-tool-choice \
  --trust-remote-code

License

MIT, following the base model. See LICENSE.

Downloads last month: 229

Safetensors

Model size

305B params

Tensor type

BF16

I64

F32

F8_E4M3

Model tree for LLMWildling/DeepSeek-V4-Flash-YoloSwag-420-preview

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

(173)

this model