Instructions to use RDson/Llama-3-Peach-Instruct-4x8B-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RDson/Llama-3-Peach-Instruct-4x8B-MoE with Transformers:

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

pipe = pipeline("text-generation", model="RDson/Llama-3-Peach-Instruct-4x8B-MoE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RDson/Llama-3-Peach-Instruct-4x8B-MoE")
model = AutoModelForCausalLM.from_pretrained("RDson/Llama-3-Peach-Instruct-4x8B-MoE")
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

vLLM

How to use RDson/Llama-3-Peach-Instruct-4x8B-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RDson/Llama-3-Peach-Instruct-4x8B-MoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RDson/Llama-3-Peach-Instruct-4x8B-MoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RDson/Llama-3-Peach-Instruct-4x8B-MoE

SGLang

How to use RDson/Llama-3-Peach-Instruct-4x8B-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 "RDson/Llama-3-Peach-Instruct-4x8B-MoE" \
    --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": "RDson/Llama-3-Peach-Instruct-4x8B-MoE",
		"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 "RDson/Llama-3-Peach-Instruct-4x8B-MoE" \
        --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": "RDson/Llama-3-Peach-Instruct-4x8B-MoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RDson/Llama-3-Peach-Instruct-4x8B-MoE with Docker Model Runner:
```
docker model run hf.co/RDson/Llama-3-Peach-Instruct-4x8B-MoE
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-Peach-Instruct-4x8B-MoE

GGUF files are available here: RDson/Llama-3-Peach-Instruct-4x8B-MoE-GGUF.

This is a experimental MoE created using Mergekit from

Evaluation: Q4_K_M:

GSM8K (5-shot): 0.6983 ± 0.0126
GSM8K (8-shot, cot): 0.674 ± 0.0129

Mergekit yaml file:

base_model: Meta-Llama-3-8B-Instruct
experts:
  - source_model: Meta-Llama-3-8B-Instruct
    positive_prompts:
    - "explain"
    - "chat"
    - "assistant"
    - "think"
    - "roleplay"
    - "versatile"
    - "helpful"
    - "factual"
    - "integrated"
    - "adaptive"
    - "comprehensive"
    - "balanced"
    negative_prompts:
    - "specialized"
    - "narrow"
    - "focused"
    - "limited"
    - "specific"
  - source_model: Llama-3-8B-Instruct-Coder
    positive_prompts:
    - "python"
    - "math"
    - "solve"
    - "code"
    - "programming"
    - "javascript"
    - "algorithm"
    - "factual"
    negative_prompts:
    - "sorry"
    - "cannot"
    - "concise"
    - "imaginative"
    - "creative"
  - source_model: SFR-Iterative-DPO-LLaMA-3-8B-R
    positive_prompts:
    - "AI"
    - "instructive"
    - "chat"
    - "assistant"
    - "clear"
    - "directive"
    - "helpful"
    - "informative"
  - source_model: Hermes-2-Theta-Llama-3-8B
    positive_prompts:
    - "chat"
    - "assistant"
    - "analytical"
    - "accurate"
    - "code"
    - "logical"
    - "knowledgeable"
    - "precise"
    - "calculate"
    - "compute"
    - "solve"
    - "work"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
    - "tell me"
    - "assistant"
    - "factual"
    negative_prompts:
    - "abstract"
    - "artistic"
    - "emotional"
    - "mistake"
    - "inaccurate"
gate_mode: hidden
dtype: float16

Some inspiration for the Mergekit yaml file is from LoneStriker/Umbra-MoE-4x10.7-2.4bpw-h6-exl2.

Downloads last month: 7

Safetensors

Model size

25B params

Tensor type

F16

Model tree for RDson/Llama-3-Peach-Instruct-4x8B-MoE

Quantizations

1 model