Seed OSS 36B Instruct
Seed OSS 36B InstructSeed-OSS is a large language models developed by ByteDance's Seed Team, designed for powerful long-context, reasoning, agent and general capabilities.
Model details
View repositoryExample usage
This example code shows how to call Seed OSS 36B Instruct using the openAI client. You can also make requests to the /predict endpoint with a message or /v1/completions endpoint with a prompt. You can also add a thinking budget using a thinking budget.
The thinking budget defaults to -1, which initiates the model with unlimited length for thinking. If a thinking budget is specified, users are advised to prioritize values that are integer multiples of 512 (e.g., 512, 1K, 2K, 4K, 8K, or 16K), as the model has been extensively trained on these intervals. Models are instructed to output a direct response when the thinking budget is 0, and we recommend setting any budget below 512 to this value.
1response = client.chat.completions.create(
2 model="ByteDance-Seed/Seed-OSS-36B-Instruct",
3 stream=stream,
4 messages=[{"role": "user", "content": "How to make pasta?"}],
5 max_tokens=4096,
6 temperature=1.1,
7 top_p=0.95,
8 extra_body={
9 "chat_template_kwargs": {
10 "thinking_budget": thinking_budget
11 }
12 }
13 )1# You can use this model with any of the OpenAI clients in any language!
2# Simply change the API Key to get started
3
4from openai import OpenAI
5model_id = "YOUR_MODEL_ID_HERE"
6client = OpenAI(
7 api_key="YOUR_API_KEY",
8 base_url=f"https://model-{model_id}.api.baseten.co/environments/production/sync/v1"
9)
10
11response = client.chat.completions.create(
12 model="ByteDance-Seed/Seed-OSS-36B-Instruct",
13 messages=[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Write FizzBuzz in Python"}],
14)
15
16print(response.choices[0].message.content)1{
2 "id": "143",
3 "choices": [
4 {
5 "finish_reason": "stop",
6 "index": 0,
7 "logprobs": null,
8 "message": {
9 "content": "[Model output here]",
10 "role": "assistant",
11 "audio": null,
12 "function_call": null,
13 "tool_calls": null
14 }
15 }
16 ],
17 "created": 1741224586,
18 "model": "",
19 "object": "chat.completion",
20 "service_tier": null,
21 "system_fingerprint": null,
22 "usage": {
23 "completion_tokens": 145,
24 "prompt_tokens": 38,
25 "total_tokens": 183,
26 "completion_tokens_details": null,
27 "prompt_tokens_details": null
28 }
29}
