Instructions to use fhnw/Llama-3-pineapple-2x8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fhnw/Llama-3-pineapple-2x8B with Transformers:

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

pipe = pipeline("text-generation", model="fhnw/Llama-3-pineapple-2x8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fhnw/Llama-3-pineapple-2x8B")
model = AutoModelForCausalLM.from_pretrained("fhnw/Llama-3-pineapple-2x8B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fhnw/Llama-3-pineapple-2x8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fhnw/Llama-3-pineapple-2x8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fhnw/Llama-3-pineapple-2x8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fhnw/Llama-3-pineapple-2x8B

SGLang

How to use fhnw/Llama-3-pineapple-2x8B 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 "fhnw/Llama-3-pineapple-2x8B" \
    --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": "fhnw/Llama-3-pineapple-2x8B",
		"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 "fhnw/Llama-3-pineapple-2x8B" \
        --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": "fhnw/Llama-3-pineapple-2x8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fhnw/Llama-3-pineapple-2x8B with Docker Model Runner:
```
docker model run hf.co/fhnw/Llama-3-pineapple-2x8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-pineapple-2x8B

Llama-3-pineapple-2x8B is a Mixture of Experts (MoE) made with the following models:

Configuration

base_model: fhnw/Llama-3-8B-pineapple-pizza-orpo
experts:
- source_model: fhnw/Llama-3-8B-pineapple-pizza-orpo
  positive_prompts: ["assistant", "chat"]
- source_model: fhnw/Llama-3-8B-pineapple-recipe-sft
  positive_prompts: ["recipe"]
gate_mode: hidden
dtype: float16

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "fhnw/Llama-3-pineapple-2x8B"

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(device)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Is pineapple on a pizza a crime?"}
]

input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))