Calibrate using the https://huggingface.co/datasets/timdettmers/openassistant-guanaco/blob/main/openassistant_best_replies_eval.jsonl dataset.
The quantization configuration is as follows

quant_config = QuantizeConfig(bits=4, group_size=128, desc_act=False)

【vLLM Startup Command】

vllm serve JunHowie/Seed-OSS-36B-Instruct-GPTQ-Int4

【Dependencies】

vllm>=0.10.2
transformers>=4.56.1

【Model Download】

python

from huggingface_hub import snapshot_download
snapshot_download('JunHowie/Seed-OSS-36B-Instruct-GPTQ-Int4', cache_dir="your_local_path")

【Overview】

Introduction

👋 Hi, everyone!
We are ByteDance Seed Team.

You can get to know us better through the following channels👇

seed logo

Seed-OSS Open-Source Models

[!NOTE] This model card is dedicated to the Seed-OSS-36B-Instruct model.

News

[2025/08/20]🔥We release Seed-OSS-36B-Base (both with and without synthetic data versions) and Seed-OSS-36B-Instruct.

Introduction

Seed-OSS is a series of open-source large language models developed by ByteDance's Seed Team, designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features. Although trained with only 12T tokens, Seed-OSS achieves excellent performance on several popular open benchmarks.

We release this series of models to the open-source community under the Apache-2.0 license.

[!NOTE] Seed-OSS is primarily optimized for international (i18n) use cases.

Key Features

Flexible Control of Thinking Budget: Allowing users to flexibly adjust the reasoning length as needed. This capability of dynamically controlling the reasoning length enhances inference efficiency in practical application scenarios.
Enhanced Reasoning Capability: Specifically optimized for reasoning tasks while maintaining balanced and excellent general capabilities.
Agentic Intelligence: Performs exceptionally well in agentic tasks such as tool-using and issue resolving.
Research-Friendly: Given that the inclusion of synthetic instruction data in pre-training may affect the post-training research, we released pre-trained models both with and without instruction data, providing the research community with more diverse options.
Native Long Context: Trained with up-to-512K long context natively.

Model Summary

Seed-OSS adopts the popular causal language model architecture with RoPE, GQA attention, RMSNorm and SwiGLU activation.


	Seed-OSS-36B
Parameters	36B
Attention	GQA
Activation Function	SwiGLU
Number of Layers	64
Number of QKV Heads	80 / 8 / 8
Head Size	128
Hidden Size	5120
Vocabulary Size	155K
Context Length	512K
RoPE Base Frequency	1e7

Evaluation Results

Seed-OSS-36B-Base

Incorporating synthetic instruction data into pretraining leads to improved performance on most benchmarks. We adopt the version augmented with synthetic instruction data (i.e., w/ syn.) as Seed-OSS-36B-Base. We also release Seed-OSS-36B-Base-woSyn trained without such data (i.e., w/o syn.), offering the community a high-performance foundation model unaffected by synthetic instruction data.

Benchmark	^Seed1.6-Base	^{Qwen3-30B-A3B-Base-2507*}	^{Qwen2.5-32B-Base*}	^{Seed-OSS-36B-Base (w/ syn.)}	^{Seed-OSS-36B-Base-woSyn (w/o syn.)}
Knowledge
MMLU-Pro	70	59.8	58.5 (55.1)	65.1	60.4
MMLU	88.8	82.7	84 (83.3)	84.9	84.8
TriviaQA	91	76.2	76	82.1	81.9
GPQA-D	43.4	37	29.3	31.7	35.2
SimpleQA	17.1	7.2	6.1	5.8	7.4
Reasoning
BBH	92.1	81.4	79.1 (84.5)	87.7	87.2
AGIEval-en	78	66.4	65.6	70.7	70.1
Math
GSM8K	93.1	87	87.5 (92.9)	90.8	90.3
MATH	72.9	61.1	63.5 (57.7)	81.7	61.3
Coding
MBPP	83.6	78.8	77.8 (84.5)	80.6	74.6
HumanEval	78	70.7	47.6 (58.5)	76.8	75.6

^{- Bold denotes open-source SOTA.}
^{- "*" indicates that the results in this column are presented in the format of "reproduced_results (reported_results_if_any)".}

Seed-OSS-36B-Instruct

Benchmark	^{Seed1.6-Thinking-0715}	^OAI-OSS-20B*	^{Qwen3-30B-A3B-Thinking-2507*}	^Qwen3-32B*	^Gemma3-27B	^{Seed-OSS-36B-Instruct}
Knowledge
MMLU-Pro	86.6	76.2	81.9 (80.9)	81.8	67.5	82.7
MMLU	90.6	81.7 (85.3)	86.9	86.2	76.9	87.4
GPQA-D	80.7	72.2 (71.5)	71.4 (73.4)	66.7 (68.4)	42.4	71.4
SuperGPQA	63.4	50.1	57.3 (56.8)	49.3	-	55.7
SimpleQA	23.7	6.7	23.6	8.6	10	9.7
Math
AIME24	90.3	92.7 (92.1)	87.7	82.7 (81.4)	-	91.7
AIME25	86	90.3 (91.7)	81.3 (85)	73.3 (72.9)	-	84.7
BeyondAIME	60	69	56	29	-	65
Reasoning
ArcAGI V2	50.3	41.7	37.8	14.4	-	40.6
KORBench	74.8	72.3	70.2	65.4	-	70.6
Coding
LiveCodeBench v6 ^{(02/2025-05/2025)}	66.8	63.8	60.3 (66)	53.4	-	67.4
HLE	13.9	12.7 (10.9)	8.7	6.9	-	10.1
Instruction Following
IFEval	86.3	92.8	88 (88.9)	88.4 (85)	90.4	85.8
Agent
TAU1-Retail	63	(54.8)	58.7 (67.8)	40.9	-	70.4
TAU1-Airline	49	(38)	47 (48)	38	-	46
SWE-Bench Verified ^(OpenHands)	41.8	(60.7)	31	23.4	-	56
SWE-Bench Verified ^{(AgentLess 4*10)}	48.4	-	33.5	39.7	-	47
Multi-SWE-Bench	17.7	-	9.5	7.7	-	17
Multilingualism
MMMLU	84.3	77.4 (75.7)	79	79 (80.6)	-	78.4
Long Context
RULER ^(128K)	94.5	78.7	94.5	77.5	-	94.6
Safety
AIR-Bench	-	-	-	-	-	75.6

^{- Bold denotes open-source SOTA. Underlined indicates the second place in the open-source model.}
^{- "*" indicates that the results in this column are presented in the format of "reproduced_results (reported_results_if_any)". Some results have been omitted due to the failure of the evaluation run.}
^{- The results of Gemma3-27B are sourced directly from its technical report.}
^{- Generation configs for Seed-OSS-36B-Instruct: temperature=1.1, top_p=0.95. Specifically, for Taubench, temperature=1, top_p=0.7.}

[!NOTE] We recommend sampling with temperature=1.1 and top_p=0.95.

Thinking Budget

Users can flexibly specify the model's thinking budget. The figure below shows the performance curves across different tasks as the thinking budget varies. For simpler tasks (such as IFEval), the model's chain of thought (CoT) is shorter, and the score exhibits fluctuations as the thinking budget increases. For more challenging tasks (such as AIME and LiveCodeBench), the model's CoT is longer, and the score improves with an increase in the thinking budget.

Here is an example with a thinking budget set to 512: during the reasoning process, the model periodically triggers self-reflection to estimate the consumed and remaining budget, and delivers the final response once the budget is exhausted or the reasoning concludes.

<seed:think>
Got it, let's try to solve this problem step by step. The problem says ... ...
<seed:cot_budget_reflect>I have used 129 tokens, and there are 383 tokens remaining for use.</seed:cot_budget_reflect>
Using the power rule, ... ...
<seed:cot_budget_reflect>I have used 258 tokens, and there are 254 tokens remaining for use.</seed:cot_budget_reflect>
Alternatively, remember that ... ...
<seed:cot_budget_reflect>I have used 393 tokens, and there are 119 tokens remaining for use.</seed:cot_budget_reflect>
Because if ... ...
<seed:cot_budget_reflect>I have exhausted my token budget, and now I will start answering the question.</seed:cot_budget_reflect>
</seed:think>
To solve the problem, we start by using the properties of logarithms to simplify the given equations: (full answer omitted).

If no thinking budget is set (default mode), Seed-OSS will initiate thinking with unlimited length. 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.

Quick Start

shell

pip3 install -r requirements.txt
pip install git+ssh://git@github.com/Fazziekey/transformers.git@seed-oss

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import os
import re

model_name_or_path = "ByteDance-Seed/Seed-OSS-36B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto")  # You may want to use bfloat16 and/or move to GPU here
messages = [
    {"role": "user", "content": "How to make pasta?"},
]
tokenized_chat = tokenizer.apply_chat_template(
  messages, 
  tokenize=True, 
  add_generation_prompt=True, 
  return_tensors="pt", 
  thinking_budget=512 # control the thinking budget
)

outputs = model.generate(tokenized_chat.to(model.device), max_new_tokens=2048)

output_text = tokenizer.decode(outputs[0])

Inference

Download Model

Download Seed-OSS checkpoint to ./Seed-OSS-36B-Instruct

Transformers

The generate.py script provides a simple interface for model inference with configurable options.

Basic Usage

shell

cd inference
python3 generate.py --model_path /path/to/model

Key Parameters

Parameter	Description
`--model_path`	Path to the pretrained model directory (required)
`--prompts`	Input prompts (default: sample cooking/code questions)
`--max_new_tokens`	Maximum tokens to generate (default: 4096)
`--attn_implementation`	Attention mechanism: `flash_attention_2` (default) or `eager`
`--load_in_4bit/8bit`	Enable 4-bit/8-bit quantization (reduces memory usage)
`--thinking_budget`	Thinking budget in tokens (default: -1 for unlimited budget)

Quantization Examples

shell

# 8-bit quantization
python3 generate.py --model_path /path/to/model --load_in_8bit True

# 4-bit quantization
python3 generate.py --model_path /path/to/model --load_in_4bit True

Custom Prompts

python3 generate.py --model_path /path/to/model --prompts "['What is machine learning?', 'Explain quantum computing']"

vLLM

Use vllm >= 0.10.0 or higher for inference.

First install vLLM with Seed-OSS support version:

VLLM_USE_PRECOMPILED=1 VLLM_TEST_USE_PRECOMPILED_NIGHTLY_WHEEL=1 pip install git+ssh://git@github.com/FoolPlayer/vllm.git@seed-oss

Start vLLM API server:

shell

python3 -m vllm.entrypoints.openai.api_server \
    --host localhost \
    --port 4321 \
    --enable-auto-tool-choice \
    --tool-call-parser seed_oss \
    --trust-remote-code \
    --model ./Seed-OSS-36B-Instruct \
    --chat-template ./Seed-OSS-36B-Instruct/chat_template.jinja \
    --tensor-parallel-size 8 \
    --dtype bfloat16 \
    --served-model-name seed_oss

Test with OpenAI client:

Chat

python3 inference/vllm_chat.py

Tool Call

python3 inference/vllm_tool_call.py

Model Card

See MODEL_CARD.

License

This project is licensed under Apache-2.0. See the LICENSE flie for details.

Citation

bibtex

@misc{seed2025seed-oss,
  author={ByteDance Seed Team},
  title={Seed-OSS Open-Source Models},
  year={2025},
  howpublished={\url{https://github.com/ByteDance-Seed/seed-oss}}
}

About ByteDance Seed Team

Founded in 2023, ByteDance Seed Team is dedicated to crafting the industry's most advanced AI foundation models. The team aspires to become a world-class research team and make significant contributions to the advancement of science and society.