Instructions to use HoomanBio2021/LabOpen-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HoomanBio2021/LabOpen-v1 with Transformers:

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

pipe = pipeline("text-generation", model="HoomanBio2021/LabOpen-v1")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("HoomanBio2021/LabOpen-v1")
model = AutoModelForMultimodalLM.from_pretrained("HoomanBio2021/LabOpen-v1", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HoomanBio2021/LabOpen-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HoomanBio2021/LabOpen-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HoomanBio2021/LabOpen-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HoomanBio2021/LabOpen-v1

SGLang

How to use HoomanBio2021/LabOpen-v1 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 "HoomanBio2021/LabOpen-v1" \
    --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": "HoomanBio2021/LabOpen-v1",
		"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 "HoomanBio2021/LabOpen-v1" \
        --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": "HoomanBio2021/LabOpen-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HoomanBio2021/LabOpen-v1 with Docker Model Runner:
```
docker model run hf.co/HoomanBio2021/LabOpen-v1
```

HoomanBio commited on 5 days ago

Commit

cd961c1

verified ·

1 Parent(s): 151f498

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ LabOpen v1 adds six verifiable capability domains (fluid physics, materials mixt
 - **Base model**: Qwen3.8-27B (FP8 release, Apache 2.0)
 - **Training**: 15 reinforcement windows (G69–G84), LoRA r=4, group-relative RL (RLOO-style, k=8 sampling) with mechanically verifiable rewards
 - **License**: Apache 2.0 (same as base)
-- **Hardware target**: FP8-capable GPUs (e.g., NVIDIA H100 / DGX GB10 class); ~31 GB in FP8
 ## Positioning & Philosophy
@@ -37,8 +37,6 @@ The project does not aim to replace general-purpose large language models. It se
 The model is intended for universities, research institutes, corporate R&D centers, and professional laboratories, and supports local or private deployment scaled to the institution's actual computing resources.
 ## What's in this repo
 | Path | Content |
@@ -110,6 +108,8 @@ vllm serve HoomanBio2021/Qwen3.8-27B-LabOpen-v1
 The merged checkpoint uses the same blockwise FP8 (e4m3, 128×128 scales) format as the base — any runtime that loads `Qwen/Qwen3.8-27B-FP8` loads this without changes.
 **Deployment notes (tested on vLLM 0.27.1):** give domain-computation requests `max_tokens ≥ 4096` — the model reasons before answering, and a 1024 budget is exhausted by the reasoning chain (`finish_reason=length`, empty content). With vLLM's `--reasoning-parser qwen3` the final answer arrives in `content` and reasoning in `reasoning_content`.
 ### The adapter (research artifact — not a serving path)
@@ -208,7 +208,7 @@ LabOpen v1 在 [Qwen/Qwen3.8-27B-FP8](https://huggingface.co/Qwen/Qwen3.8-27B-FP
 - **基座模型**：Qwen3.8-27B（FP8 版本，Apache 2.0）
 - **训练**：15 个强化窗口（G69–G84），LoRA r=4，组相对强化学习（RLOO 式，k=8 采样），机械可验证奖励
 - **许可证**：Apache 2.0（与基座相同）
-- **硬件要求**：支持 FP8 的 GPU（如 NVIDIA H100 / DGX GB10 等级别）；FP8 下约 31 GB
 ## 项目定位与理念
@@ -218,7 +218,6 @@ Qwen3.8-27B-LabOpen v1 是基于 Qwen3.8-27B 开源基础模型开展领域微
 模型主要面向高校、科研院所、企业研发中心及专业实验室等使用场景，支持根据实际计算资源条件进行本地化或私有化部署。
 ## 仓库内容
 | 路径 | 内容 |
@@ -290,6 +289,8 @@ vllm serve HoomanBio2021/Qwen3.8-27B-LabOpen-v1
 合并检查点与基座采用完全相同的分块 FP8（e4m3，128×128 块尺度）格式——任何能加载 `Qwen/Qwen3.8-27B-FP8` 的运行时均可直接加载本仓库，无需改动。
 **部署要点（已在 vLLM 0.27.1 实测）**：域计算请求的 `max_tokens` 应给到 **4096 以上**——模型先思考后作答，1024 预算会被思考链耗尽（`finish_reason=length`、正文为空）。vLLM 配 `--reasoning-parser qwen3` 时，最终答案在 `content`、推理在 `reasoning_content`。
 ### 适配器（研究工件——非服务路径）
@@ -373,4 +374,4 @@ vllm serve HoomanBio2021/Qwen3.8-27B-LabOpen-v1
 ## 联系方式
-如有任何问题，请提交问题反馈或联系 [research.ai@xthinktank.com](mailto:research.ai@xthinktank.com)。

 - **Base model**: Qwen3.8-27B (FP8 release, Apache 2.0)
 - **Training**: 15 reinforcement windows (G69–G84), LoRA r=4, group-relative RL (RLOO-style, k=8 sampling) with mechanically verifiable rewards
 - **License**: Apache 2.0 (same as base)
+- **Hardware target**: NVIDIA GPUs with compute capability ≥ 8.9 (H100 / L40S / B200 / DGX GB10 class); ~31 GB in FP8
 ## Positioning & Philosophy
 The model is intended for universities, research institutes, corporate R&D centers, and professional laboratories, and supports local or private deployment scaled to the institution's actual computing resources.
 ## What's in this repo
 | Path | Content |
 The merged checkpoint uses the same blockwise FP8 (e4m3, 128×128 scales) format as the base — any runtime that loads `Qwen/Qwen3.8-27B-FP8` loads this without changes.
+**Hardware support:** requires NVIDIA compute capability ≥ 8.9 (Hopper / Ada / Blackwell — e.g. H100, L40S, B200, DGX GB10; tested on DGX GB10). Ampere and older (A100, RTX 3090) have no FP8 support. Single-card memory must fit ~31 GB of weights (48 GB minimum with reduced context, 80 GB recommended); multi-GPU tensor parallel works. No macOS path — vLLM has no Apple-Silicon backend and no Mac runtime loads this blockwise-FP8 checkpoint format.
 **Deployment notes (tested on vLLM 0.27.1):** give domain-computation requests `max_tokens ≥ 4096` — the model reasons before answering, and a 1024 budget is exhausted by the reasoning chain (`finish_reason=length`, empty content). With vLLM's `--reasoning-parser qwen3` the final answer arrives in `content` and reasoning in `reasoning_content`.
 ### The adapter (research artifact — not a serving path)
 - **基座模型**：Qwen3.8-27B（FP8 版本，Apache 2.0）
 - **训练**：15 个强化窗口（G69–G84），LoRA r=4，组相对强化学习（RLOO 式，k=8 采样），机械可验证奖励
 - **许可证**：Apache 2.0（与基座相同）
+- **硬件要求**：NVIDIA 计算能力 ≥ 8.9 的 GPU（H100 / L40S / B200 / DGX GB10 等级别）；FP8 下约 31 GB
 ## 项目定位与理念
 模型主要面向高校、科研院所、企业研发中心及专业实验室等使用场景，支持根据实际计算资源条件进行本地化或私有化部署。
 ## 仓库内容
 | 路径 | 内容 |
 合并检查点与基座采用完全相同的分块 FP8（e4m3，128×128 块尺度）格式——任何能加载 `Qwen/Qwen3.8-27B-FP8` 的运行时均可直接加载本仓库，无需改动。
+**硬件支持**：需要 NVIDIA 计算能力 ≥ 8.9（Hopper / Ada / Blackwell——如 H100、L40S、B200、DGX GB10；已在 DGX GB10 实测）。Ampere 及更早（A100、RTX 3090）无 FP8 支持。单卡显存需容纳约 31 GB 权重（最低 48 GB 并缩短上下文，推荐 80 GB）；支持多卡张量并行。无 macOS 路径——vLLM 无 Apple Silicon 后端，且无 Mac 运行时能加载本分块 FP8 检查点格式。
 **部署要点（已在 vLLM 0.27.1 实测）**：域计算请求的 `max_tokens` 应给到 **4096 以上**——模型先思考后作答，1024 预算会被思考链耗尽（`finish_reason=length`、正文为空）。vLLM 配 `--reasoning-parser qwen3` 时，最终答案在 `content`、推理在 `reasoning_content`。
 ### 适配器（研究工件——非服务路径）
 ## 联系方式
+如有任何问题，请提交问题反馈或联系 [research.ai@xthinktank.com](mailto:research.ai@xthinktank.com)。