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

Libraries

How to use grimjim/Nemo-Instruct-2407-baked-v1-12B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Nemo-Instruct-2407-baked-v1-12B")
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-baked-v1-12B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Nemo-Instruct-2407-baked-v1-12B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

docker model run hf.co/grimjim/Nemo-Instruct-2407-baked-v1-12B

SGLang

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

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

Nemo-Instruct-2407-baked-v1-12B

This model represents an attempt to "bake in" the effect of a system prompt via directional contrasting and subsequent by addition of the directions to layers 10 through 34. Weight magnitudes/norms were preserved during this intervention, a technique which seems to work well for Nemo 12B. There were no projection and orthogonalization steps, as the goal was to shift the course of default activations in response to a prompt.

The system prompt used was:

Default to statements over questions, disagree when you actually disagree, and don't guide the user toward answers you expect. In roleplay, respond as the character would naturally react rather than accommodating every user action, and advance scenes through character behavior rather than questions.

The dual goal was to discourage undue sycophancy and engagement while also promoting authenticity in roleplay. It was the hope that this would at least partially counter or neutrailze biases that were the result of Instruct training.

More details forthcoming.

Downloads last month: -

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for grimjim/Nemo-Instruct-2407-baked-v1-12B

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Finetuned

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

Finetuned

(1)

this model

Quantizations

2 models