Instructions to use grimjim/Nemo-Instruct-2407-MPOA-v4-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Nemo-Instruct-2407-MPOA-v4-12B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Nemo-Instruct-2407-MPOA-v4-12B")
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-v4-12B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Nemo-Instruct-2407-MPOA-v4-12B", device_map="auto")
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/Nemo-Instruct-2407-MPOA-v4-12B 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-v4-12B"
# 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-v4-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/Nemo-Instruct-2407-MPOA-v4-12B

SGLang

How to use grimjim/Nemo-Instruct-2407-MPOA-v4-12B 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-v4-12B" \
    --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-v4-12B",
		"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-v4-12B" \
        --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-v4-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/Nemo-Instruct-2407-MPOA-v4-12B with Docker Model Runner:
```
docker model run hf.co/grimjim/Nemo-Instruct-2407-MPOA-v4-12B
```

Nemo-Instruct-2407-MPOA-v4-12B / README.md

grimjim

Upload folder using huggingface_hub

d9860bf verified 9 months ago

preview code

Raw

History Blame Contribute Delete

992 Bytes

metadata

license: apache-2.0
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ru
  - zh
  - ja
base_model:
  - mistralai/Mistral-Nemo-Instruct-2407
pipeline_tag: text-generation
library_name: transformers

Nemo-Instruct-2407-MPOA-v4-12B

MPOA (Magnitude-Preserving Othogonalized Ablation, AKA norm-preserving biprojected abliteration) has been applied to layers 10-34 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.

The harmless/baseline set used contains Chinese, English, and French prompts; the harmful/contrast set contains Chinese, English, and French prompts. English text generation remains coherent.

An experiment with adding German prompts to both sets, for a fourth language in total, resulted in a model with excessive repetition, and will not be released.