Instructions to use crestf411/MN-SlushoMix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use crestf411/MN-SlushoMix with Transformers:

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

pipe = pipeline("text-generation", model="crestf411/MN-SlushoMix")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("crestf411/MN-SlushoMix")
model = AutoModelForCausalLM.from_pretrained("crestf411/MN-SlushoMix")
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 crestf411/MN-SlushoMix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "crestf411/MN-SlushoMix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "crestf411/MN-SlushoMix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/crestf411/MN-SlushoMix

SGLang

How to use crestf411/MN-SlushoMix 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 "crestf411/MN-SlushoMix" \
    --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": "crestf411/MN-SlushoMix",
		"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 "crestf411/MN-SlushoMix" \
        --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": "crestf411/MN-SlushoMix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use crestf411/MN-SlushoMix with Docker Model Runner:
```
docker model run hf.co/crestf411/MN-SlushoMix
```

A bit more information

by GhostGate - opened Nov 21, 2024

Discussion

GhostGate

Nov 21, 2024

Hi!

It would be great to have a bit more information on what is achieved with this model. What is the purpose of the merge and what is the outcome of it.

crestf411

Owner Nov 21, 2024

The model is an illusion. You should avoid it.

GhostGate

Nov 22, 2024

Is it meant as merge fodder, or do you mean it's a test and not ready for anything official?

crestf411

Owner Nov 22, 2024

It was requested by a user. Since the slush model isn’t just a LoRA it’s not trivial to apply it to existing models.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment