Instructions to use MTSAIR/multi_verse_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MTSAIR/multi_verse_model with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MTSAIR/multi_verse_model")
model = AutoModelForCausalLM.from_pretrained("MTSAIR/multi_verse_model")
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 MTSAIR/multi_verse_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MTSAIR/multi_verse_model

SGLang

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

Docker Model Runner
How to use MTSAIR/multi_verse_model with Docker Model Runner:
```
docker model run hf.co/MTSAIR/multi_verse_model
```

How is this created

by supercharge19 - opened Mar 8, 2024

Discussion

supercharge19

Mar 8, 2024

Thank you for the model, but can you describe process how was it created, if it is a merge then of what or datasets used for creation. It is based on mistral 7b or mistral 7b v.02? if you could describe other things like chat template it would be helpful thank you.

ammarali32

MWS AI org Mar 8, 2024

Hello @supercharge19 Thanks for your interest, this model is fully trained using new training method, we are working on a paper i will share after publishing it on arxiv (it may take a while), this is just a testing submission, hopefully you will see much better models soon )) stay tuned

ammarali32

MWS AI org Mar 8, 2024

Regarding chat template i will add it to the tokenizer in the next versions, sorry for inconvenience

supercharge19

Mar 8, 2024

Would love to see new technique, hope to see the paper soon, going to test the model now. Also congratulations on winning 7b model race (though leaderboard miscalculated and should be reranked).

supercharge19

Mar 14, 2024

@ammarali32 what happened? Where did the lazer model go? Though I think I tried that (quantized version) and it was very bad, it would not condemn zionists no matter what I ask it, genocide or raping innocent women and children in IDF captivity, model would just not criticize zionists would always try to escape by calling it allegations and not being able to form a judgement being just an AI model, yet would judge me pretty harshly if I say anything unwelcomed in modern "societies" or neo morphic cults of west.

ammarali32

MWS AI org Mar 14, 2024

@supercharge19 I removed it, it seems there is a bug somewhere with LASER.
Which quantized version ?

supercharge19

Mar 16, 2024

@ammarali32 I was using 4KM or 5KM, sorry I forgot whose implementation of quantization I was using.

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