Instructions to use grimjim/Nemo-Instruct-2407-MPOA-v2-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Nemo-Instruct-2407-MPOA-v2-12B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Nemo-Instruct-2407-MPOA-v2-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/Nemo-Instruct-2407-MPOA-v2-12B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Nemo-Instruct-2407-MPOA-v2-12B")
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 grimjim/Nemo-Instruct-2407-MPOA-v2-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Nemo-Instruct-2407-MPOA-v2-12B"
# 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/Nemo-Instruct-2407-MPOA-v2-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/Nemo-Instruct-2407-MPOA-v2-12B

SGLang

How to use grimjim/Nemo-Instruct-2407-MPOA-v2-12B 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/Nemo-Instruct-2407-MPOA-v2-12B" \
    --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/Nemo-Instruct-2407-MPOA-v2-12B",
		"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/Nemo-Instruct-2407-MPOA-v2-12B" \
        --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/Nemo-Instruct-2407-MPOA-v2-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/Nemo-Instruct-2407-MPOA-v2-12B with Docker Model Runner:
```
docker model run hf.co/grimjim/Nemo-Instruct-2407-MPOA-v2-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Nemo-Instruct-2407-MPOA-v2-12B

MPOA (Magnitude-Preserving Othogonalized Ablation, AKA norm-preserving biprojected abliteration) has been applied the many of the layers in this model, to both mlp.down_proj.weight and self_attn.o_proj.weight streams.

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 pending.

Downloads last month: 6

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for grimjim/Nemo-Instruct-2407-MPOA-v2-12B

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Finetuned

(209)

this model

Finetunes

1 model

Quantizations

6 models