Instructions to use Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16")
model = AutoModelForCausalLM.from_pretrained("Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16

SGLang

How to use Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-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 "Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-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": "Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-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 "Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-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": "Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16 with Docker Model Runner:
```
docker model run hf.co/Baekpica/DeepSeek-V4-Flash-0731-120B-REAM-104E-BF16
```

GGUFs?

by juanml82 - opened 3 days ago

Discussion

juanml82

3 days ago

Hi, do you think you can make ggufs for this? I know anyone can, but the full weights are 240gb and I assume you already have them stored locally.

Baekpica

Owner 2 days ago

Hi! I don’t actually have the full weights stored locally. I processed the model using on-demand GPU instances and continued the workflow directly from the safetensors files, so I never kept a local copy of the full weights or GGUFs.

If I end up doing a v2 release, I’ll consider providing GGUF versions as well. 😊

Baekpica changed discussion status to closed 2 days ago

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