Instructions to use CloudGoat/Baphomet-1.0-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CloudGoat/Baphomet-1.0-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="CloudGoat/Baphomet-1.0-4B")
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/Baphomet-1.0-4B")
model = AutoModelForMultimodalLM.from_pretrained("CloudGoat/Baphomet-1.0-4B", 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/Baphomet-1.0-4B 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/Baphomet-1.0-4B:Q8_0
# Run inference directly in the terminal:
llama cli -hf CloudGoat/Baphomet-1.0-4B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CloudGoat/Baphomet-1.0-4B:Q8_0
# Run inference directly in the terminal:
llama cli -hf CloudGoat/Baphomet-1.0-4B: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 CloudGoat/Baphomet-1.0-4B:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf CloudGoat/Baphomet-1.0-4B: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 CloudGoat/Baphomet-1.0-4B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CloudGoat/Baphomet-1.0-4B:Q8_0

Use Docker

docker model run hf.co/CloudGoat/Baphomet-1.0-4B:Q8_0

LM Studio
Jan

vLLM

How to use CloudGoat/Baphomet-1.0-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CloudGoat/Baphomet-1.0-4B"
# 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/Baphomet-1.0-4B",
		"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/Baphomet-1.0-4B:Q8_0

SGLang

How to use CloudGoat/Baphomet-1.0-4B 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/Baphomet-1.0-4B" \
    --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/Baphomet-1.0-4B",
		"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/Baphomet-1.0-4B" \
        --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/Baphomet-1.0-4B",
		"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/Baphomet-1.0-4B with Ollama:
```
ollama run hf.co/CloudGoat/Baphomet-1.0-4B:Q8_0
```
Unsloth Desktop

How to use CloudGoat/Baphomet-1.0-4B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CloudGoat/Baphomet-1.0-4B: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/Baphomet-1.0-4B:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CloudGoat/Baphomet-1.0-4B with Docker Model Runner:
```
docker model run hf.co/CloudGoat/Baphomet-1.0-4B:Q8_0
```

Lemonade

How to use CloudGoat/Baphomet-1.0-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CloudGoat/Baphomet-1.0-4B:Q8_0

Run and chat with the model

lemonade run user.Baphomet-1.0-4B-Q8_0

List all available models

lemonade list

Hermes Agent

How to use CloudGoat/Baphomet-1.0-4B 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/Baphomet-1.0-4B: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/Baphomet-1.0-4B:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CloudGoat/Baphomet-1.0-4B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CloudGoat/Baphomet-1.0-4B: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/Baphomet-1.0-4B: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"

Baphomet-1.0-4B

Linear merge of 8 task-vectors based on Qwen3.5-4B

Base	Method	Task-Vectors	Output
`Qwen/Qwen3.5-4B`	`linear` (goatmerge)	8 vectors, 0.1375 each	`safetensors ×10`, `Q8_0 GGUF`

1. Overview

Baphomet-1.0-4B is a model produced by linearly combining 8 task-vectors (T = W_donor − W_base) into the base model Qwen/Qwen3.5-4B. According to a 2025 paper (hitit et al., 2025) on model merging, pure Task Arithmetic is the only method that consistently improves performance across "in-the-wild" models. Based on that paper, I merged high-quality community fine-tuned versions of Qwen3.5-4B.

W_merged = W_base + Σ αᵢ · Tᵢ   (αᵢ = 0.1375)

The configured weights sum to 0.1375 × 8 = 1.10. According to goatmerge.json, normalize: true, rescale: true are enabled, so normalized coefficients are applied. Refer to the goatmerge implementation for the exact computation.

No claim is made about improved performance or inheritance of specific capabilities. No quantitative evaluation has been performed.

2. Merge configuration

2.1 Base model and settings

Item	Value
Base	`Qwen/Qwen3.5-4B`
Base fingerprint	`62de7a218d003afe6dffca82532c20150488b68ec629e72f9b50a0615dd7c8c5`
Tool	goatmerge (format v1.1.0)
Method	`linear`, `density=1.0`, `normalize=true`, `rescale=true`
Chunk	`8388608` elements, `drop_caches=true`

2.2 Task-vector list (α = 0.1375 each)

The table below transcribes the extraction source (source_model) recorded in each TV's goatmerge.json. No statement of effect is made.

#	Task-vector	Recorded source_model
1	`Agents-A1-4B-TV`	`InternScience/Agents-A1-4B`
2	`DeepSeek-V4-Pro-Qwen3.5-4B-TV`	`Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B`
3	`Qwen3.8-4B-Distill-TV`	`empero-ai/Qwen3.8-4B-Distill`
4	`Qwopus3.5-4B-Coder-TV`	`Jackrong/Qwopus3.5-4B-Coder`
5	`Qwopus3.5-4B-v3-TV`	`Jackrong/Qwopus3.5-4B-v3`
6	`AREX-Turbo-TV`	`BAAI/AREX-Turbo`
7	`NeoHorse-1-4B-TV`	`NeoHorse-1-4B-Aligned` (key-converted `TokenRhythm/NeoHorse-1-4B`)
8	`tmax-4B-TV`	`allenai/tmax-4b`

recipe.yaml (for reproduction)

base: Qwen/Qwen3.5-4B
out: ./Baphomet-1.0-4B-k8

merge_method: linear
chunk_elements: 8388608
drop_caches: true
skip_fingerprint_check: false

tv:
  - dir: ./Task-Vectors/Agents-A1-4B-TV
    weight: 0.1375
  - dir: ./Task-Vectors/DeepSeek-V4-Pro-Qwen3.5-4B-TV
    weight: 0.1375
  - dir: ./Task-Vectors/Qwen3.8-4B-Distill-TV
    weight: 0.1375
  - dir: ./Task-Vectors/Qwopus3.5-4B-Coder-TV
    weight: 0.1375
  - dir: ./Task-Vectors/Qwopus3.5-4B-v3-TV
    weight: 0.1375
  - dir: ./Task-Vectors/AREX-Turbo-TV
    weight: 0.1375
  - dir: ./Task-Vectors/NeoHorse-1-4B-TV
    weight: 0.1375
  - dir: ./Task-Vectors/tmax-4B-TV
    weight: 0.1375

Note: NeoHorse-1-4B uses a text-only key layout, so its keys were converted from model.* to model.language_model.* with align_neohorse.py before extraction. See Section 5 of the parent directory README for details.

3. Model specifications

Excerpt from config.json.

Item	Value
Architecture	`Qwen3_5ForConditionalGeneration`
Text layers	32 layers, hidden size `2560`, heads `16Q / 4KV (GQA)`, `head_dim 256`
Attention layer types	Repeating pattern of 3 `linear_attention` layers followed by 1 `full_attention` layer
FFN	`intermediate 9216`, `SiLU`, `tie_word_embeddings: true`
Vocabulary size	`248,320` (`Qwen2Tokenizer`, BPE)
Context length	`262,144` (RoPE θ=`10000000`, interleaved M-RoPE)
Vision	hidden size `1024`, 24 layers, `patch_size 16`, `spatial_merge_size 2`, `temporal_patch_size 2`
Special tokens	`<
Dtype	`bfloat16` (safetensors)

4. Included files

File	Size	Description
`model-00001-of-00010.safetensors` through `model-00010…`	Approx. 8.9GB total	Model weights (bf16, 10 shards)
`model.safetensors.index.json`	66KB	Shard index
`Baphomet-1.0-4B-q8_0.gguf`	4.2GB	Q8_0 quantization for llama.cpp
`config.json`	3.1KB	Model configuration
`tokenizer.json` / `vocab.json` / `merges.txt`	13MB / 6.5MB / 3.2MB	Tokenizer
`tokenizer_config.json` / `chat_template.jinja`	17KB / 7.6KB	Chat template
`preprocessor_config.json`	390B	`Qwen3VLProcessor` configuration
`goatmerge.json`	1.6KB	Merge provenance (fingerprint, TV list)

5. Usage

5.1 Transformers (safetensors)

from transformers import AutoModelForVision2Seq, AutoProcessor

model_id = "Baphomet-1.0-4B"  # Replace with a local path or repository name

model = AutoModelForVision2Seq.from_pretrained(
    model_id,
    dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

messages = [
    {"role": "user", "content": [
        {"type": "image", "image": "https://example.com/cat.png"},
        {"type": "text", "text": "Describe this image in English."},
    ]},
]
inputs = processor.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(out[0], skip_special_tokens=False))

5.2 llama.cpp (GGUF)

# Interactive chat
llama-cli -m Baphomet-1.0-4B-q8_0.gguf -cnv -c 8192

# Server mode
llama-server -m Baphomet-1.0-4B-q8_0.gguf -c 32768 --port 8080

5.3 vLLM

vllm serve ./Baphomet-1.0-4B-k8 --max-model-len 32768 --trust-remote-code

Chat format example

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Write a parallel downloader in Rust<|im_end|>
<|im_start|>assistant
<think>
Organizing the requirements…
</think>
```rust
// code here
```<|im_end|>

Tool calls may be emitted in <tool_call><function=…> form and reasoning in <think>…</think>. Refer to chat_template.jinja for the exact format.

6. Benchmark

Status: In progress. Evaluation is underway. No results are reported yet, and this card makes no performance claims until measured values are recorded below.

Suite	Condition	Base (`Qwen/Qwen3.5-4B`)	Baphomet-1.0-4B	Notes
TBD	Same prompts and settings as base	TBD	TBD	To be recorded with harness version, seed, and date
TBD	Same prompts and settings as base	TBD	TBD	To be recorded with harness version, seed, and date

Results, when available, will be recorded here with the evaluation date, harness and dataset versions, sampling parameters, and number of runs. The base model will be evaluated under identical conditions for comparison.

7. Limitations

The model is the result of a linear merge; there is no guarantee that characteristics of individual donor models are preserved.
It may inherit the license terms and biases of each donor and the base model. Determine the scope of use after reviewing the license of each model.
Benchmark evaluation is in progress (see Section 6). No results are reported yet, and no performance claims are made.
Use for final decisions in high-risk domains such as medical or legal matters is not intended.

8. Credits

Role	Model
Base	Qwen/Qwen3.5-4B
Donors	InternScience/Agents-A1-4B, Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B, empero-ai/Qwen3.8-4B-Distill, Jackrong/Qwopus3.5-4B-Coder, Jackrong/Qwopus3.5-4B-v3, BAAI/AREX-Turbo, TokenRhythm/NeoHorse-1-4B, allenai/tmax-4b
Merge tool	GoatMerge
References	O. K. Hitit, C. Sankar, Y. K. Kim, A. Risteski, and A. Elgohary, "A systematic study of in-the-wild model merging for large language models," arXiv preprint arXiv:2511.21437, 2025.