Instructions to use liminerity/mm4-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liminerity/mm4-3b with Transformers:

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

pipe = pipeline("text-generation", model="liminerity/mm4-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liminerity/mm4-3b")
model = AutoModelForCausalLM.from_pretrained("liminerity/mm4-3b")
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 liminerity/mm4-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liminerity/mm4-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/mm4-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/liminerity/mm4-3b

SGLang

How to use liminerity/mm4-3b 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 "liminerity/mm4-3b" \
    --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": "liminerity/mm4-3b",
		"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 "liminerity/mm4-3b" \
        --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": "liminerity/mm4-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use liminerity/mm4-3b with Docker Model Runner:
```
docker model run hf.co/liminerity/mm4-3b
```

question

by mrfakename - opened Mar 20, 2024

Discussion

mrfakename

Mar 20, 2024

hi,
this model looks super cool! would you mind sharing what model it's based on?
thanks!

gate369

liminerity org Mar 21, 2024

liminerity/dhbacmes-3b-slerp-fine-tuned-2
liminerity/herbaccbaccules-3b-slerp-finetuned

merged together and finetuned for like 8 hours on a t4 using axolotl on google collab. i honestly have no idea what im doing but im trying to understand what ive even been making i just follow tutorials and papers i read

mrfakename

Mar 21, 2024

nice, thank you! is this model instruct/chat-tuned?

gate369

liminerity org Mar 21, 2024

yes but it isnt the best. i used teknium/GPT4-LLM-Cleaned data set. I honestly do not know how well it performs by memory

mrfakename

Mar 21, 2024

Ah, nice. Thank you so much!

mrfakename changed discussion status to closed Mar 21, 2024

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