Instructions to use spmurrayzzz/clefsift with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spmurrayzzz/clefsift with Transformers:

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

pipe = pipeline("text-classification", model="spmurrayzzz/clefsift")
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("spmurrayzzz/clefsift")
model = AutoModelForMultimodalLM.from_pretrained("spmurrayzzz/clefsift", 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

llama.cpp

How to use spmurrayzzz/clefsift 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 spmurrayzzz/clefsift:Q8_0
# Run inference directly in the terminal:
llama cli -hf spmurrayzzz/clefsift:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf spmurrayzzz/clefsift:Q8_0
# Run inference directly in the terminal:
llama cli -hf spmurrayzzz/clefsift:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf spmurrayzzz/clefsift:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf spmurrayzzz/clefsift:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf spmurrayzzz/clefsift:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf spmurrayzzz/clefsift:Q8_0

Use Docker

docker model run hf.co/spmurrayzzz/clefsift:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use spmurrayzzz/clefsift with Ollama:
```
ollama run hf.co/spmurrayzzz/clefsift:Q8_0
```
Unsloth Desktop

How to use spmurrayzzz/clefsift with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf spmurrayzzz/clefsift:Q8_0

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": "spmurrayzzz/clefsift:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use spmurrayzzz/clefsift with Docker Model Runner:
```
docker model run hf.co/spmurrayzzz/clefsift:Q8_0
```

Lemonade

How to use spmurrayzzz/clefsift with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull spmurrayzzz/clefsift:Q8_0

Run and chat with the model

lemonade run user.clefsift-Q8_0

List all available models

lemonade list

Hermes Agent

How to use spmurrayzzz/clefsift with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf spmurrayzzz/clefsift:Q8_0

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 spmurrayzzz/clefsift:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use spmurrayzzz/clefsift with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf spmurrayzzz/clefsift:Q8_0

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 "spmurrayzzz/clefsift:Q8_0" \
  --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"

clefsift

File size: 1,461 Bytes

df424c1

{
  "model": "ClefSift",
  "repo_id": "spmurrayzzz/clefsift",
  "experiment": "clef-27b-llmtrace-en-fourway-v2",
  "checkpoint_step": 128,
  "base_model": "Cloudflare/clef",
  "base_revision": "2f3de3dd85f379784083b0814d997ab627200f0c",
  "architecture": "Qwen3_5ForConditionalGeneration",
  "backbone_dtype": "bfloat16",
  "joint_head_dtype": "float32",
  "joint_schema_model_sha256": "0e304cf7c6500e8bb59bef7e2afd2c6373f82596dfb3b57d1aa93c175e2dc3a3",
  "training": {
    "toolkit": "clef-finetune",
    "toolkit_version": "0.1.0",
    "seed": 0,
    "steps": 128,
    "example_exposures": 512,
    "lora_rank": 64,
    "lora_alpha": 128,
    "lora_dropout": 0.05,
    "gradient_accumulation": 4,
    "learning_rate": 0.0001,
    "head_learning_rate": 0.00005,
    "max_request_tokens": 1536
  },
  "dataset": {
    "source": "iitolstykh/LLMTrace_detection",
    "revision": "332053804f8798177ff2ecb1148e1839ed429ba3",
    "language": "en",
    "training_groups": 298,
    "training_rows": 1192,
    "labels": ["human", "ai-assisted", "mixed", "ai"],
    "label_status": "provisional",
    "source_rights_status": "not-independently-cleared"
  },
  "gguf": {
    "path": "ClefSift-Q8_0.gguf",
    "quantization": "Q8_0",
    "bytes": 28732214816,
    "sha256": "1fbdedec7989395973e5364a47dcd4a01a5f419a425b26ba476faed5556cb7fa",
    "llama_cpp_commit": "a46709b683aba9274d8ab29f5b42f7e551d1dff6",
    "llama_cpp_build": 11450
  },
  "license": "apache-2.0"
}