Instructions to use SuperbEmphasis/mn-12b-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SuperbEmphasis/mn-12b-test with Transformers:

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

pipe = pipeline("text-generation", model="SuperbEmphasis/mn-12b-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SuperbEmphasis/mn-12b-test")
model = AutoModelForCausalLM.from_pretrained("SuperbEmphasis/mn-12b-test")
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 SuperbEmphasis/mn-12b-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SuperbEmphasis/mn-12b-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SuperbEmphasis/mn-12b-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SuperbEmphasis/mn-12b-test

SGLang

How to use SuperbEmphasis/mn-12b-test 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 "SuperbEmphasis/mn-12b-test" \
    --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": "SuperbEmphasis/mn-12b-test",
		"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 "SuperbEmphasis/mn-12b-test" \
        --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": "SuperbEmphasis/mn-12b-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SuperbEmphasis/mn-12b-test with Docker Model Runner:
```
docker model run hf.co/SuperbEmphasis/mn-12b-test
```

MN-12b-RP-Ink

This is a merge of pre-trained language models created using mergekit. I have removed several of the unsused layers as a test. The model still works but it can catch itself into a loop. I am attempting to finetune the model on a longer conversational dataset to see if that issue can be resolved.

I would NOT use this model... It is for testing purposes only.

Merge Details

Merge Method

This model was merged using the Passthrough merge method.

Models Merged

The following models were included in the merge:

/storage/bases/MN-12b-RP-Ink

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 27]
        model: /storage/bases/MN-12b-RP-Ink
    - sources:
      - layer_range: [29, 30]
        model: /storage/bases/MN-12b-RP-Ink
    - sources:
      - layer_range: [32, 40]
        model: /storage/bases/MN-12b-RP-Ink

Downloads last month: 2

Safetensors

Model size

11B params

Tensor type

BF16