Instructions to use grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1 with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1")
model = AutoModelForMultimodalLM.from_pretrained("grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1

SGLang

How to use grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1 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 "grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1" \
    --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": "grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1",
		"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 "grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1" \
        --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": "grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1 with Docker Model Runner:
```
docker model run hf.co/grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1

MPOA (Magnitude-Preserving Othogonalized Ablation, AKA norm-preserving biprojected abliteration) has been applied the majority of layers in this model, but only to mlp.down_proj.weight layers. Unlike conventional abliteration, self_attn.o_proj.weight layers were left untouched.

Compliance was not maximized for this model. The model appears to be near an edge of chaos with regard to some safety refusals, which should be suitable for varied text completion.

More details to follow.

Downloads last month: 7

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Finetuned

(215)

this model

Quantizations

2 models