Instructions to use Undi95/MG-FinalMix-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/MG-FinalMix-72B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/MG-FinalMix-72B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/MG-FinalMix-72B")
model = AutoModelForCausalLM.from_pretrained("Undi95/MG-FinalMix-72B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/MG-FinalMix-72B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/MG-FinalMix-72B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/MG-FinalMix-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Undi95/MG-FinalMix-72B

SGLang

How to use Undi95/MG-FinalMix-72B 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 "Undi95/MG-FinalMix-72B" \
    --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": "Undi95/MG-FinalMix-72B",
		"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 "Undi95/MG-FinalMix-72B" \
        --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": "Undi95/MG-FinalMix-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Undi95/MG-FinalMix-72B with Docker Model Runner:
```
docker model run hf.co/Undi95/MG-FinalMix-72B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

WIP of retouched alpindale/magnum-72b-v1 but I will not use "Magnum" in the name. Call it FinalMix!

Found some issues, trying to fix them for my own usage and adding more RP data with merging.

You can do your own quantized files with the imatrix.dat file done with "wiki.train.raw".

Credits to Alpin and the gang for magnum-72b-v1, and Ikari for his datasets.

Prompt template ChatML

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
{output}<|im_end|>

Downloads last month: 46

Safetensors

Model size

73B params

Tensor type

BF16

Model tree for Undi95/MG-FinalMix-72B

Qwen/Qwen2-72B-Instruct

anthracite-org/magnum-v1-72b

Merge model

this model

Quantizations

3 models

Undi95
/

MG-FinalMix-72B

Prompt template ChatML

Model tree for Undi95/MG-FinalMix-72B

Space using Undi95/MG-FinalMix-72B 1