Instructions to use yleo/EmertonMonarch-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yleo/EmertonMonarch-7B with Transformers:

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

pipe = pipeline("text-generation", model="yleo/EmertonMonarch-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yleo/EmertonMonarch-7B")
model = AutoModelForCausalLM.from_pretrained("yleo/EmertonMonarch-7B")
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 yleo/EmertonMonarch-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yleo/EmertonMonarch-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yleo/EmertonMonarch-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yleo/EmertonMonarch-7B

SGLang

How to use yleo/EmertonMonarch-7B 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 "yleo/EmertonMonarch-7B" \
    --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": "yleo/EmertonMonarch-7B",
		"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 "yleo/EmertonMonarch-7B" \
        --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": "yleo/EmertonMonarch-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yleo/EmertonMonarch-7B with Docker Model Runner:
```
docker model run hf.co/yleo/EmertonMonarch-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🦜 EmertonMonarch-7B

EmertonOmniBeagle-7B-dpo is a DPO fine-tune of mlabonne/Monarch-7B using the yleo/emerton_dpo_pairs_judge preference dataset created from Intel/orca_dpo_pairs by replacing gpt 3.5 answer by a gpt4 Turbo answer. Then, LLM-Blender is used to judge between GPT4 and GPT4 Turbo.

🔍 Applications

This model uses a context window of 8k. It is compatible with different templates, like chatml and Llama's chat template.

🏆 Evaluation

Open LLM Leaderboard

To come...

💻 Usage

!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "yleo/EmertonMonarch-7B"
messages = [{"role": "user", "content": "How to improve LLM fine-tuning?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
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"])