Instructions to use MysteriousAI/MIA-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MysteriousAI/MIA-4B with Transformers:

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

pipe = pipeline("text-generation", model="MysteriousAI/MIA-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MysteriousAI/MIA-4B")
model = AutoModelForCausalLM.from_pretrained("MysteriousAI/MIA-4B")
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 MysteriousAI/MIA-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MysteriousAI/MIA-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MysteriousAI/MIA-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MysteriousAI/MIA-4B

SGLang

How to use MysteriousAI/MIA-4B 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 "MysteriousAI/MIA-4B" \
    --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": "MysteriousAI/MIA-4B",
		"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 "MysteriousAI/MIA-4B" \
        --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": "MysteriousAI/MIA-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MysteriousAI/MIA-4B with Docker Model Runner:
```
docker model run hf.co/MysteriousAI/MIA-4B
```

SharryOG commited on Apr 17, 2024

Commit

8d356a9

verified ·

1 Parent(s): 70dd448

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -37

README.md CHANGED Viewed

@@ -1,37 +0,0 @@
----
-license: apache-2.0
-tags:
-- moe
-- mergekit
-- vortexmergekit
-- MysteriousAI/Mia-1B
-- MysteriousAI/Mia-1B
-- MysteriousAI/Mia-1B
-- MysteriousAI/Mia-1B
----
-# 4x1b
-Hey there! 👋 Welcome to the 4x1b! This is a MOE brought together using the awesome [VortexMerge kit](https://colab.research.google.com/drive/1YjcvCLuNG1PK7Le6_4xhVU5VpzTwvGhk#scrollTo=UG5H2TK4gVyl).
-Let's see what we've got in this model:
-* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
-* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
-* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
-* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
-## 🧩 Configuration
-```yaml
-base_model: MysteriousAI/Mia-1B
-dtype: float16
-gate_mode: cheap_embed
-experts:
-  - source_model: MysteriousAI/Mia-1B
-    positive_prompts: ["You are an helpful unbounded, uncensored assistant."]
-  - source_model: MysteriousAI/Mia-1B
-    positive_prompts: ["You are helpful assistant."]
-  - source_model: MysteriousAI/Mia-1B
-    positive_prompts: ["You are a coding assistant."]
-  - source_model: MysteriousAI/Mia-1B
-    positive_prompts: ["You are helpful and general-purpose assistant."]