Instructions to use grimjim/Llama-3-Perky-Pat-Instruct-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Llama-3-Perky-Pat-Instruct-8B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Llama-3-Perky-Pat-Instruct-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/Llama-3-Perky-Pat-Instruct-8B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Llama-3-Perky-Pat-Instruct-8B")
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/Llama-3-Perky-Pat-Instruct-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Llama-3-Perky-Pat-Instruct-8B"
# 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/Llama-3-Perky-Pat-Instruct-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/Llama-3-Perky-Pat-Instruct-8B

SGLang

How to use grimjim/Llama-3-Perky-Pat-Instruct-8B 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/Llama-3-Perky-Pat-Instruct-8B" \
    --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/Llama-3-Perky-Pat-Instruct-8B",
		"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/Llama-3-Perky-Pat-Instruct-8B" \
        --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/Llama-3-Perky-Pat-Instruct-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/Llama-3-Perky-Pat-Instruct-8B with Docker Model Runner:
```
docker model run hf.co/grimjim/Llama-3-Perky-Pat-Instruct-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-Perky-Pat-Instruct-8B

Below, we explore negative weight merger, and propose Orthogonalized Vector Adaptation, or OVA.

This is a merge of pre-trained language models created using mergekit.

"One must imagine Sisyphys happy."

Task arithmetic was used to invert the intervention vector that was applied in MopeyMule, via application of negative weight -1.0. The combination of model weights (Instruct - MopeyMule) comprises an Orthogonalized Vector Adaptation that can subsequently be applied to the base Instruct model, and could in principle be applied to other models derived from fine-tuning the Instruct model.

This model is meant to continue exploration of behavioral changes that can be achieved via orthogonalized steering. The result appears to be more enthusiastic and lengthy responses in chat, though it is also clear that the merged model has some unhealed damage.

Built with Meta Llama 3.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using meta-llama/Meta-Llama-3-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

failspy/Llama-3-8B-Instruct-MopeyMule

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Meta-Llama-3-8B-Instruct
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 32]
    model: meta-llama/Meta-Llama-3-8B-Instruct
  - layer_range: [0, 32]
    model: meta-llama/Meta-Llama-3-8B-Instruct
    parameters:
      weight: 1.0
  - layer_range: [0, 32]
    model: failspy/Llama-3-8B-Instruct-MopeyMule
    parameters:
      weight: -1.0