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

Libraries

How to use ByteDance-Seed/Seed-Coder-8B-Reasoning with Transformers:

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

pipe = pipeline("text-generation", model="ByteDance-Seed/Seed-Coder-8B-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ByteDance-Seed/Seed-Coder-8B-Reasoning")
model = AutoModelForCausalLM.from_pretrained("ByteDance-Seed/Seed-Coder-8B-Reasoning", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ByteDance-Seed/Seed-Coder-8B-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance-Seed/Seed-Coder-8B-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/Seed-Coder-8B-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ByteDance-Seed/Seed-Coder-8B-Reasoning

SGLang

How to use ByteDance-Seed/Seed-Coder-8B-Reasoning 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/Seed-Coder-8B-Reasoning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/Seed-Coder-8B-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Seed-Coder-8B-Reasoning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/Seed-Coder-8B-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

yuyuzhang commited on Apr 30, 2025

Commit

13911cf

verified ·

1 Parent(s): 53d0dbb

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -12

README.md CHANGED Viewed

@@ -37,27 +37,28 @@ pip install -U transformers accelerate
 Here is a simple example demonstrating how to load the model and perform code generation using the Hugging Face `pipeline` API:
 ```python
-import transformers
 import torch
 model_id = "ByteDance-Seed/Seed-Coder-8B-Reasoning"
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model_id,
-    model_kwargs={"torch_dtype": torch.bfloat16},
-    device_map="auto",
-)
 messages = [
-    {"role": "user", "content": "Solve the following problem: Given an array of integers, find two numbers such that they add up to a specific target number."},
 ]
-outputs = pipeline(
     messages,
-    max_new_tokens=512,
-)
-print(outputs[0]["generated_text"][-1]["content"])
 ```
 ## Evaluation

 Here is a simple example demonstrating how to load the model and perform code generation using the Hugging Face `pipeline` API:
 ```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 model_id = "ByteDance-Seed/Seed-Coder-8B-Reasoning"
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
 messages = [
+    {"role": "user", "content": "Write a quick sort algorithm."},
 ]
+input_ids = tokenizer.apply_chat_template(
     messages,
+    tokenize=True,
+    return_tensors="pt",
+    add_generation_prompt=True,
+).to(model.device)
+outputs = model.generate(input_ids, max_new_tokens=32768)
+response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
+print(response)
 ```
 ## Evaluation