Instructions to use cellsentry-team/cellsentry-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use cellsentry-team/cellsentry-model with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cellsentry-team/cellsentry-model
# Run inference directly in the terminal:
llama cli -hf cellsentry-team/cellsentry-model

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cellsentry-team/cellsentry-model
# Run inference directly in the terminal:
llama cli -hf cellsentry-team/cellsentry-model

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf cellsentry-team/cellsentry-model
# Run inference directly in the terminal:
./build/bin/llama cli -hf cellsentry-team/cellsentry-model

Use Docker

docker model run hf.co/cellsentry-team/cellsentry-model

Llama new
LM Studio
Jan

vLLM

How to use cellsentry-team/cellsentry-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/cellsentry-team/cellsentry-model

Ollama
How to use cellsentry-team/cellsentry-model with Ollama:
```
ollama run hf.co/cellsentry-team/cellsentry-model
```
Unsloth Desktop

How to use cellsentry-team/cellsentry-model with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cellsentry-team/cellsentry-model

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "cellsentry-team/cellsentry-model"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use cellsentry-team/cellsentry-model with Docker Model Runner:
```
docker model run hf.co/cellsentry-team/cellsentry-model
```

Lemonade

How to use cellsentry-team/cellsentry-model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cellsentry-team/cellsentry-model

Run and chat with the model

lemonade run user.cellsentry-model-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use cellsentry-team/cellsentry-model with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cellsentry-team/cellsentry-model

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default cellsentry-team/cellsentry-model

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use cellsentry-team/cellsentry-model with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cellsentry-team/cellsentry-model

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "cellsentry-team/cellsentry-model" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Legacy Qwen2.5-1.5B v3 — Compatibility Model

English

Repository status

This is a historical multi-task generative checkpoint, retained for existing downloads and rollback. It is not one of the newly separated mmBERT classifiers. Current mmBERT research is managed in separate restricted-access repositories pending review; no default application model is changed by this organization cleanup.

The actually hosted artifact is cellsentry-1.5b-v3-q4km.gguf: 986047968 bytes, SHA256 4ae17b3886e4a5089671bf16aa133eaa6d8917a118bde6c75a54c1c3610f7cd3. It contains merged Qwen-based inference weights. There is no MLX checkpoint or LoRA adapter in the current file inventory; older “MLX coming soon” text is not a delivery claim.

Download and use

hf download cellsentry-team/cellsentry-model cellsentry-1.5b-v3-q4km.gguf --local-dir models

Use a compatible llama.cpp runtime and the task-specific Qwen ChatML/JSON protocol expected by the calling application. Historical tasks were formula-alert review, PII detection and structured extraction; their protocols and evaluation are distinct. This GGUF is not interchangeable with mmBERT encoder-plus-head checkpoints.

Some legacy local workflows still use this pinned artifact. Do not infer the current CellSentry or Vibli default solely from the repository name, and do not replace an application's configured model solely by changing a file path. Historical training descriptions are not new validation, general PII recall, or a production accuracy guarantee.

Historical documentation and license

The complete pre-cleanup model card remains available at the fixed historical revision. The weight bytes and download path are unchanged. The existing MIT metadata and upstream Qwen attribution are retained; this cleanup does not relicense or retrain the model.

中文

仓库状态

这是为既有下载与回滚保留的历史多任务生成模型，不属于新拆分的 mmBERT 分类器。新的 mmBERT 研究工件在独立受限仓内整理，尚待后续确认；本次组织整理不切换应用默认模型。

当前实际文件为 cellsentry-1.5b-v3-q4km.gguf，986047968 字节，SHA256 4ae17b3886e4a5089671bf16aa133eaa6d8917a118bde6c75a54c1c3610f7cd3，已包含合并后的 Qwen 推理权重。仓内没有 MLX checkpoint 或 LoRA adapter，旧文案中的“即将提供 MLX”不代表已经交付。

下载与使用

下载命令见英文部分。使用兼容 llama.cpp 的运行时及调用方要求的 Qwen ChatML／JSON 协议。历史任务包含公式告警复核、PII 和结构化抽取，协议与评测各不相同；此 GGUF 不能直接替换 mmBERT 编码器与独立分类头。

部分历史本机流程仍使用此固定文件。不能按仓名猜测 CellSentry 或 Vibli 当前默认模型，也不能仅换路径完成模型迁移。历史训练描述不等于新验证、完整 PII 召回或生产准确率保证。

历史文档与许可

整理前完整模型卡见英文部分固定历史版本链接。权重字节和下载路径不变；保留既有 MIT 元数据与 Qwen 上游署名，本次不重新许可或训练。

Downloads last month: 160

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for cellsentry-team/cellsentry-model

Base model

Qwen/Qwen2.5-1.5B

Adapter

(494)

this model