Instructions to use ByteDance-Seed/Stable-DiffCoder-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance-Seed/Stable-DiffCoder-8B-Base with Transformers:

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

pipe = pipeline("text-generation", model="ByteDance-Seed/Stable-DiffCoder-8B-Base", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("ByteDance-Seed/Stable-DiffCoder-8B-Base", trust_remote_code=True)
model = AutoModel.from_pretrained("ByteDance-Seed/Stable-DiffCoder-8B-Base", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ByteDance-Seed/Stable-DiffCoder-8B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance-Seed/Stable-DiffCoder-8B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/Stable-DiffCoder-8B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ByteDance-Seed/Stable-DiffCoder-8B-Base

SGLang

How to use ByteDance-Seed/Stable-DiffCoder-8B-Base 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 "ByteDance-Seed/Stable-DiffCoder-8B-Base" \
    --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": "ByteDance-Seed/Stable-DiffCoder-8B-Base",
		"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 "ByteDance-Seed/Stable-DiffCoder-8B-Base" \
        --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": "ByteDance-Seed/Stable-DiffCoder-8B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ByteDance-Seed/Stable-DiffCoder-8B-Base with Docker Model Runner:
```
docker model run hf.co/ByteDance-Seed/Stable-DiffCoder-8B-Base
```

Seas0 commited on Mar 9

Commit

a9092b2

unverified ·

1 Parent(s): 5514ede

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -52,9 +52,9 @@ This repo contains the **Stable-DiffCoder-8B-Base** model, which has the followi
 |  Stable-DiffCoder-8B-Instruct  | 8K    | 🤗 [Model](https://huggingface.co/ByteDance-Seed/Stable-DiffCoder-8B-Instruct)   |  Instruction-tuned for alignment with user intent. |
 ## Requirements
-You need to install a specific version of `transformers` to adapt to the inference process:
 ```bash
-pip install transformers==4.46.2
 ```
 ## Explanation of Inference Parameters
 - `steps`: Number of steps for diffusion generation
@@ -144,4 +144,4 @@ If you find our work helpful, feel free to give us a cite.
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2601.15892},
 }
-```

 |  Stable-DiffCoder-8B-Instruct  | 8K    | 🤗 [Model](https://huggingface.co/ByteDance-Seed/Stable-DiffCoder-8B-Instruct)   |  Instruction-tuned for alignment with user intent. |
 ## Requirements
+Current (v5.3.0) `transformers` is available for inference:
 ```bash
+pip install transformers~=5.3.0
 ```
 ## Explanation of Inference Parameters
 - `steps`: Number of steps for diffusion generation
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2601.15892},
 }
+```