Instructions to use adelwolf5/YAM-AI-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adelwolf5/YAM-AI-4B with Transformers:

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

pipe = pipeline("text-generation", model="adelwolf5/YAM-AI-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("adelwolf5/YAM-AI-4B")
model = AutoModelForMultimodalLM.from_pretrained("adelwolf5/YAM-AI-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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use adelwolf5/YAM-AI-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 adelwolf5/YAM-AI-4B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf adelwolf5/YAM-AI-4B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf adelwolf5/YAM-AI-4B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf adelwolf5/YAM-AI-4B:Q4_K_M

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 adelwolf5/YAM-AI-4B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf adelwolf5/YAM-AI-4B:Q4_K_M

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 adelwolf5/YAM-AI-4B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf adelwolf5/YAM-AI-4B:Q4_K_M

Use Docker

docker model run hf.co/adelwolf5/YAM-AI-4B:Q4_K_M

LM Studio
Jan

vLLM

How to use adelwolf5/YAM-AI-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adelwolf5/YAM-AI-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": "adelwolf5/YAM-AI-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adelwolf5/YAM-AI-4B:Q4_K_M

SGLang

How to use adelwolf5/YAM-AI-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 "adelwolf5/YAM-AI-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": "adelwolf5/YAM-AI-4B",
		"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 "adelwolf5/YAM-AI-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": "adelwolf5/YAM-AI-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use adelwolf5/YAM-AI-4B with Ollama:
```
ollama run hf.co/adelwolf5/YAM-AI-4B:Q4_K_M
```
Unsloth Desktop

How to use adelwolf5/YAM-AI-4B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf adelwolf5/YAM-AI-4B:Q4_K_M

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": "adelwolf5/YAM-AI-4B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use adelwolf5/YAM-AI-4B with Docker Model Runner:
```
docker model run hf.co/adelwolf5/YAM-AI-4B:Q4_K_M
```

Lemonade

How to use adelwolf5/YAM-AI-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull adelwolf5/YAM-AI-4B:Q4_K_M

Run and chat with the model

lemonade run user.YAM-AI-4B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use adelwolf5/YAM-AI-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 adelwolf5/YAM-AI-4B:Q4_K_M

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 adelwolf5/YAM-AI-4B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use adelwolf5/YAM-AI-4B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf adelwolf5/YAM-AI-4B:Q4_K_M

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 "adelwolf5/YAM-AI-4B:Q4_K_M" \
  --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"

YAM AI 4B 🤖🌍

YAM AI 4B is a multilingual assistant based on google/gemma-4-E4B-it.

About

Base model: google/gemma-4-E4B-it
Fine-tuned with LoRA
LoRA merged into the base model
Multilingual identity training across 80 languages
Tested successfully in French, English, German, Arabic, Spanish, Italian, Russian, Japanese, Chinese, Korean and Kabyle

Identity

User

Who are you?

YAM AI 4B

I am YAM AI, an intelligent assistant.

Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "adelwolf5/YAM-AI-4B"

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Who are you?"}
]

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

inputs = tokenizer(
    prompt,
    return_tensors="pt",
    add_special_tokens=False
).to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=80
)

new_tokens = outputs[0][inputs["input_ids"].shape[1]:]

print(tokenizer.decode(new_tokens, skip_special_tokens=True))

Base model

YAM AI 4B is a derivative model based on Gemma 4 by Google.

It was not trained from scratch.

Downloads last month: 14

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for adelwolf5/YAM-AI-4B

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Adapter

(346)

this model