Instructions to use CloudGoat/Mephisto-4B-0725 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CloudGoat/Mephisto-4B-0725 with Transformers:

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

pipe = pipeline("image-text-to-text", model="CloudGoat/Mephisto-4B-0725")
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("CloudGoat/Mephisto-4B-0725")
model = AutoModelForMultimodalLM.from_pretrained("CloudGoat/Mephisto-4B-0725", 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 CloudGoat/Mephisto-4B-0725 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 CloudGoat/Mephisto-4B-0725:Q8_0
# Run inference directly in the terminal:
llama cli -hf CloudGoat/Mephisto-4B-0725:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CloudGoat/Mephisto-4B-0725:Q8_0
# Run inference directly in the terminal:
llama cli -hf CloudGoat/Mephisto-4B-0725:Q8_0

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 CloudGoat/Mephisto-4B-0725:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf CloudGoat/Mephisto-4B-0725:Q8_0

Use Docker

docker model run hf.co/CloudGoat/Mephisto-4B-0725:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use CloudGoat/Mephisto-4B-0725 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CloudGoat/Mephisto-4B-0725"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CloudGoat/Mephisto-4B-0725",
		"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/CloudGoat/Mephisto-4B-0725:Q8_0

SGLang

How to use CloudGoat/Mephisto-4B-0725 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 "CloudGoat/Mephisto-4B-0725" \
    --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": "CloudGoat/Mephisto-4B-0725",
		"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 "CloudGoat/Mephisto-4B-0725" \
        --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": "CloudGoat/Mephisto-4B-0725",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use CloudGoat/Mephisto-4B-0725 with Ollama:
```
ollama run hf.co/CloudGoat/Mephisto-4B-0725:Q8_0
```
Unsloth Desktop

How to use CloudGoat/Mephisto-4B-0725 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CloudGoat/Mephisto-4B-0725: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": "CloudGoat/Mephisto-4B-0725:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CloudGoat/Mephisto-4B-0725 with Docker Model Runner:
```
docker model run hf.co/CloudGoat/Mephisto-4B-0725:Q8_0
```

Lemonade

How to use CloudGoat/Mephisto-4B-0725 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CloudGoat/Mephisto-4B-0725:Q8_0

Run and chat with the model

lemonade run user.Mephisto-4B-0725-Q8_0

List all available models

lemonade list

Hermes Agent

How to use CloudGoat/Mephisto-4B-0725 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CloudGoat/Mephisto-4B-0725: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 CloudGoat/Mephisto-4B-0725:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CloudGoat/Mephisto-4B-0725 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CloudGoat/Mephisto-4B-0725: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 "CloudGoat/Mephisto-4B-0725: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"

Mephisto-4B-0725

This model is currently being improved.

This is a merge of pre-trained language models created using mergekit fork. This is a merge of pre-trained language models created using mergekit. The advanced conversational EQ exhibited by Agents-A1-4B—relative to its parameter count—does not stem from a single component but rather emerges from a dense distributed representation inherent in the entire model, spanning its multiple layers; thus, Agents-A1-4B's conversational ability is encoded diffusely rather than locally. However, since the "tool-calling capability" required for agentic behavior—which Agents-A1-4B lacks—is instead localized within specific attention heads or sparse FFN layers, it is possible to merge task vectors from a model with a more localized representation of this skill, derived from Qwen3.5-4B. Furthermore, the exclusivity of task-specific regions is supported by the findings of Panigrahi et al. ("Task-Specific Skill Localization in Fine-tuned Language Models," 2023), who show that a small, identifiable subset of parameters can account for the majority of a fine-tuned model's task performance. To endow Agents-A1-4B with tool-calling capabilities, tool-calling models such as Tmax-4B and enfuse/smol-tools-4b-32k are merged using the DARE-TIES method. To preserve Agents-A1-4B's original conversational EQ—which, being diffusely distributed, is more vulnerable to disruption by naive merging—a high drop rate is applied to extract only the sharpest, most task-relevant parameters. All the aforementioned models share the same prompt format and base model. All the aforementioned models share the same prompt format and base model.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen/Qwen3.5-4B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: Qwen/Qwen3.5-4B

models:
    - model: InternScience/Agents-A1-4B
    parameters:
      weight: 1.0
      density: 1.0

  - model: allenai/tmax-4b
    parameters:
      weight: 0.7
      density: 0.3

parameters:
  int8_mask: true
  normalize: false      

dtype: bfloat16

Benchmarks

Tasks	`InternScience/Agents-A1-4B`	`CloudGoat/Mephisto-4B-0725`
JCommonsenseQA (n=300)	86.00% (±2.01%)	84.67% (±2.08%)
JNLI (n=300)	76.33% (±2.46%)	77.00% (±2.43%)
JSQuAD (n=300)	65.33% (±2.75%)	64.67% (±2.76%)
MARC-ja (n=300)	95.00% (±1.26%)	95.00% (±1.26%)
JGLUE average	80.67% (±0.00%)	80.34% (±0.00%)
GAIA Level 1 (full)	12/53	12/53