Instructions to use Isotonic/smol_llama-4x220M-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Isotonic/smol_llama-4x220M-MoE with Transformers:

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

pipe = pipeline("text-generation", model="Isotonic/smol_llama-4x220M-MoE")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Isotonic/smol_llama-4x220M-MoE")
model = AutoModelForCausalLM.from_pretrained("Isotonic/smol_llama-4x220M-MoE")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Isotonic/smol_llama-4x220M-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Isotonic/smol_llama-4x220M-MoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Isotonic/smol_llama-4x220M-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Isotonic/smol_llama-4x220M-MoE

SGLang

How to use Isotonic/smol_llama-4x220M-MoE 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 "Isotonic/smol_llama-4x220M-MoE" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Isotonic/smol_llama-4x220M-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Isotonic/smol_llama-4x220M-MoE" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Isotonic/smol_llama-4x220M-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Isotonic/smol_llama-4x220M-MoE with Docker Model Runner:
```
docker model run hf.co/Isotonic/smol_llama-4x220M-MoE
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🌟 Buying me coffee is a direct way to show support for this project.

smol_llama-4x220M-MoE

smol_llama-4x220M-MoE is a Mixure of Experts (MoE) made with the following models using LazyMergekit:

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Isotonic/smol_llama-4x220M-MoE"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.bfloat16},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

🧩 Configuration

experts:
  - source_model: BEE-spoke-data/smol_llama-220M-openhermes
    positive_prompts:
    - "reasoning"
    - "logic"
    - "problem-solving"
    - "critical thinking"
    - "analysis"
    - "synthesis"
    - "evaluation"
    - "decision-making"
    - "judgment"
    - "insight"

  - source_model: BEE-spoke-data/beecoder-220M-python
    positive_prompts:
    - "program"
    - "software"
    - "develop"
    - "build"
    - "create"
    - "design"
    - "implement"
    - "debug"
    - "test"
    - "code"
    - "python"
    - "programming"
    - "algorithm"
    - "function"

  - source_model: BEE-spoke-data/zephyr-220m-sft-full
    positive_prompts:
    - "storytelling"
    - "narrative"
    - "fiction"
    - "creative writing"
    - "plot"
    - "characters"
    - "dialogue"
    - "setting"
    - "emotion"
    - "imagination"
    - "scene"
    - "story"
    - "character"
    
  - source_model: BEE-spoke-data/zephyr-220m-dpo-full
    positive_prompts:
    - "chat"
    - "conversation"
    - "dialogue"
    - "discuss"
    - "ask questions"
    - "share thoughts"
    - "explore ideas"
    - "learn new things"
    - "personal assistant"
    - "friendly helper"

Downloads last month: 90

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for Isotonic/smol_llama-4x220M-MoE

Finetunes

1 model

Quantizations

2 models

Datasets used to train Isotonic/smol_llama-4x220M-MoE

Collection including Isotonic/smol_llama-4x220M-MoE

🧪⛙ Merged Models

Collection

A collection of merged models. • 11 items • Updated Sep 25, 2024 • 2