Instructions to use llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied with Transformers:

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

pipe = pipeline("text-generation", model="llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied")
model = AutoModelForCausalLM.from_pretrained("llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied")
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 llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied

SGLang

How to use llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied 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 "llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied" \
    --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": "llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied",
		"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 "llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied" \
        --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": "llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied with Docker Model Runner:
```
docker model run hf.co/llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied
```

ByteDance-Seed/Seed-OSS-36B-Base (llamafied)

This is a version of ByteDance-Seed/Seed-OSS-36B-Base converted to the Llama format. It should be compatible with all programs that support Llama.

Output is token-identical to the original weights when tested with bitsandbytes.

~/AI/scripts
venv ❯ python test_byte.py
ByteDance-Seed_Seed-OSS-36B-Instruct
The `load_in_4bit` and `load_in_8bit` arguments are deprecated and will be removed in the future versions. Please, pass a `BitsAndBytesConfig` object in `quantization_config` argument instead.
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:28<00:00,  1.92s/it]
The following generation flags are not valid and may be ignored: ['temperature', 'top_p']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
<seed:bos>system
You are an intelligent assistant that can answer questions in one step without the need for reasoning and thinking, that is, your thinking budget is 0. Next, please skip the thinking process and directly start answering the user's questions.
<seed:eos><seed:bos>user
How to make pasta?<seed:eos><seed:bos>assistant
<seed:think><seed:cot_budget_reflect>The current thinking budget is 0, so I will directly start answering the question.</seed:cot_budget_reflect>
</seed:think>To make pasta, follow these key steps:  


### **1. Prepare the Dough**  
- **Ingredients**: 500g (3½ cups) all-purpose or bread

venv ❯ python test_byte_llamafied.py
ByteDance-Seed_Seed-OSS-36B-Instruct-llamafied
The `load_in_4bit` and `load_in_8bit` arguments are deprecated and will be removed in the future versions. Please, pass a `BitsAndBytesConfig` object in `quantization_config` argument instead.
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 40/40 [00:19<00:00,  2.07it/s]
The following generation flags are not valid and may be ignored: ['temperature', 'top_p']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
<seed:bos>system
You are an intelligent assistant that can answer questions in one step without the need for reasoning and thinking, that is, your thinking budget is 0. Next, please skip the thinking process and directly start answering the user's questions.
<seed:eos><seed:bos>user
How to make pasta?<seed:eos><seed:bos>assistant
<seed:think><seed:cot_budget_reflect>The current thinking budget is 0, so I will directly start answering the question.</seed:cot_budget_reflect>
</seed:think>To make pasta, follow these key steps:  


### **1. Prepare the Dough**  
- **Ingredients**: 500g (3½ cups) all-purpose or bread

Downloads last month: 4

Safetensors

Model size

36B params

Tensor type

BF16

Model tree for llamafy/ByteDance-Seed_Seed-OSS-36B-Base-llamafied

Base model

ByteDance-Seed/Seed-OSS-36B-Base

Finetuned

(10)

this model