
商汤发布 SenseNova-Loop-9B 模型,以更少参数实现更深计算
来源标题:SenseNova-Loop-9B: Deeper Computation with Fewer Parameters
商汤在 Hugging Face 上线 SenseNova-Loop-9B,主打以更少参数完成更深层计算。该模型为图文转文本多模态模型,采用循环 Transformer 架构,支持中英文,采用 apache-2.0 许可,可通过 Transformers 部署使用。
以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。
Like 15
Follow
SenseNova 807
Image-Text-to-Text
Transformers
Safetensors
English
Chinese
sensenova_loop
text-generation
multimodal
looped-transformer
mhc
custom_code
conversational
License: apache-2.0
Model card Files Files and versions xet
Community 4
Deploy
Copy to bucket
Use this model Instructions to use sensenova/SenseNova-Loop-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
Libraries
Transformers How to use sensenova/SenseNova-Loop-9B with Transformers:
Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="sensenova/SenseNova-Loop-9B", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)
pip install -U transformers accelerate
Load model directly
from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("sensenova/SenseNova-Loop-9B", trust_remote_code=True, device_map="auto")
Notebooks
Google Colab
Kaggle
Local Apps Settings
vLLM How to use sensenova/SenseNova-Loop-9B with vLLM:
Install vLLM from pip:
pip install vllm
Start the vLLM server:
vllm serve "sensenova/SenseNova-Loop-9B"
Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{
"model": "sensenova/SenseNova-Loop-9B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}'
Use Docker
docker model run hf.co/sensenova/SenseNova-Loop-9B
SGLang How to use sensenova/SenseNova-Loop-9B with SGLang:
Install SGLang from pip:
pip install sglang
Start the SGLang server:
python3 -m sglang.launch_server
--model-path "sensenova/SenseNova-Loop-9B"
--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": "sensenova/SenseNova-Loop-9B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}'
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 "sensenova/SenseNova-Loop-9B"
--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": "sensenova/SenseNova-Loop-9B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}'
Docker Model Runner How to use sensenova/SenseNova-Loop-9B with Docker Model Runner:
docker model run hf.co/sensenova/SenseNova-Loop-9B
You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
SenseNova-Loop-9B 🌐 Architecture
📣 News
🚀 SenseNova-Loop-9B: Deeper Computation with Fewer Parameters Model Highlights
🎬 Showcase 3D
SVG + Web
Poster
Web
Design
📊 Model Performance: From Preview to Release
🧠 Model Architecture Model Specifications
Looped Decoder
Hybrid Attention
Two-Stream mHC
🔬 Loop Scaling: Exploring the Benefits of Looped Computation
💾 Low-Memory Deployment
Get Started Requirements
Text Generation with Transformers
Deployment
Inference Acceleration
🏋️ Training
⚠️ Known Limitations
📄 License and Citation
SenseNova-Loop-9B
English | 简体中文
📣 News
🔥 2026-11-17: We release SenseNova-Loop-9B, with model weights and code available to the community.
🔥 2026-10-31: We release SenseNova-Loop-9B-Preview, with model weights and code available to the community.
🚀 SenseNova-Loop-9B: Deeper Computation with Fewer Parameters
We officially release SenseNova-Loop-9B. Building on the Preview's exploration of parameter efficiency, the model reuses layer weights through a looped architecture and combines them with manifold-constrained hyper-connections (mHC) to expand computational depth within a compact parameter budget. It is designed for complex reasoning, coding, tool use, and multimodal tasks.
Since the Preview release, we have received community interest and feedback on model use, inference deployment, and ecosystem integration. The official release retains the looped architecture and two-stream mHC, further improving performance on agentic, coding, and data analysis tasks while continuing to explore the capabilities of looped computation.
SenseNova-Loop-9B has approximately 9B parameters. By repeatedly executing shared middle layers, it extends 32 physical decoder layers into 56 layer executions. The model accepts text and images and generates text, supporting long-context understanding and multi-step tasks. In agentic and data analysis evaluations, the model is competitive with Qwen3.8-27B: it scores 41.36 versus 44.60 on NL2Repo and 65.31 versus 65.01 on AIDABench.
Model Highlights
Shared looped block: 24 decoder layers are executed twice in sequence, producing 56 layer computations from 32 distinct layers per forward pass.
Two-stream mHC: learned mappings route and combine information between two residual streams within the looped block.
Hybrid attention: the decoder interleaves linear and full attention in a repeating four-layer pattern.
Long-context multimodal training: the training recipe includes text, images, code, and tool-use trajectories, with the context length extended to 512K tokens.
Low-memory deployment: With 4-bit weights and an 8-bit KV cache, multimodal inference at a 256K context length requires approximately 15 GiB of GPU memory.
Official quantized release: An official AWQ 4-bit version is available on launch day for easier deployment.
🎬 Showcase
3D
📊 Model Performance: From Preview to Release
We evaluate SenseNova-Loop-9B on agentic, coding, and data analysis tasks, comparing the release with the Preview and other models.
The release outperforms the Preview on all seven benchmarks shown. AutomationBench rises from 14.33 to 36.67, Terminal-Bench 2.1 from 40.45 to 59.55, and GAIA from 37.86 to 69.90.
Compared with Qwen3.8-27B, the release matches its 36.67 on AutomationBench and scores 65.31 versus 65.01 on AIDABench. On NL2Repo, it scores 41.36 versus 44.60. Its BIRD score of 72.34 is 0.96 percentage points above the Preview's 71.38.
🧠 Model Architecture
SenseNova-Loop-9B is built on a 32-layer multimodal decoder combining shared-weight looped computation, hybrid attention, and two-stream manifold-constrained hyper-connections (mHC). It extends computation depth by reusing middle-layer parameters, accepts text and images, generates text, and supports a context length of up to 512K tokens.
Model Specifications
Property SenseNova-Loop-9B
Architecture Autoregressive multimodal decoder; looped block with two-stream mHC
Parameter scale Approximately 9B total parameters; approximately 14.6B inference-equivalent parameters
Input / output Text and images / text
Distinct decoder layers 32
Looped layer range / passes [4, 28) / 2, with shared weights
Decoder layer executions 56 per forward pass
mHC residual streams 2
Context length 512K tokens
Weight precision BF16 backbone; FP32 mHC routing parameters
Looped Decoder
Inputs first pass through layers 0–3, then through the same block of layers 4–27 twice, and finally through layers 28–31 and the output head. If B denotes the looped block and h its input, the looped computation can be written as B(B(h)).
During inference, each forward pass performs 56 decoder-layer computations while storing only 32 sets of decoder-layer weights. The looped block shares the same weights across both passes, with the output of the first pass serving as input to the second.
Hybrid Attention
The decoder interleaves linear attention and full attention. Each group of four layers contains three linear-attention layers followed by one full-attention layer. The loop boundaries align with complete four-layer groups, so both passes preserve the same attention pattern.
Two-Stream mHC
Within the looped block, mHC uses two residual streams to carry information around decoder-layer computations. Learned mappings determine how each layer reads from the streams, mixes information between them, and writes its output back to the residual state. The stream-mixing map is constrained with Sinkhorn normalization, using 20 iterations in the model configuration.
The two streams can be viewed as two sets of hidden states carried in parallel. A looped layer reads from the streams, applies attention or feed-forward computation, and writes its output back. Repeated row and column normalization constrains how information is mixed between the streams. These 20 normalization iterations are internal to mHC and are separate from the two passes through the looped block.
The loop range, number of passes, and mHC routing parameters together define the checkpoint's execution configuration. A compatible inference implementation must load these parameters and preserve the same computation order.
🔬 Loop Scaling: Exploring the Benefits of Looped Computation
Looped Transformers show promising performance scaling, offering another way to expand model capability through repeated computation. Using the original 9B model with a standard single forward pass (Loop 1) as the baseline, we vary the number of loops while holding the training data and other settings constant. Overall performance improves across the four tasks, with the best results at three or four loops. AIDABench-QA and Workbuddy-office peak at three loops, improving by 6.42% and 16.93% relative to the baseline; LiveCodeBench V6 and AIDABench data visualization peak at four loops, improving by 8.10% and 8.55%.
To balance inference efficiency, both the Preview and the release use two loops by default. Deeper loops nevertheless provide further gains: moving from two to four loops improves LiveCodeBench V6 by 1.04 percentage points and AIDABench data visualization by 1.35 percentage points. These experiments cover one to four loops, leaving the potential of deeper looping open for further study.
Different tasks respond differently to loop depth. We will continue exploring deeper computation and Dynamic Loop architectures that adapt the number of loops to each input, allocating computation according to task complexity.
💾 Low-Memory Deployment
The shared looped architecture uses approximately 9B distinct parameters. With 4-bit weight quantization, the model weights occupy approximately 4.9 GB. Using an 8-bit or 4-bit KV cache can further reduce memory requirements for long-context inference. The estimated minimum GPU memory requirements for deployment are:
Get Started
Use Transformers to load the model from a Hugging Face repository or a local model directory. The examples below cove
正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。