Instructions to use shirasko/llama-3.1-8b-instruct-rmu-ancient-rome with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shirasko/llama-3.1-8b-instruct-rmu-ancient-rome with Transformers:

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

pipe = pipeline("text-generation", model="shirasko/llama-3.1-8b-instruct-rmu-ancient-rome")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shirasko/llama-3.1-8b-instruct-rmu-ancient-rome")
model = AutoModelForCausalLM.from_pretrained("shirasko/llama-3.1-8b-instruct-rmu-ancient-rome", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shirasko/llama-3.1-8b-instruct-rmu-ancient-rome with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shirasko/llama-3.1-8b-instruct-rmu-ancient-rome"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shirasko/llama-3.1-8b-instruct-rmu-ancient-rome",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shirasko/llama-3.1-8b-instruct-rmu-ancient-rome

SGLang

How to use shirasko/llama-3.1-8b-instruct-rmu-ancient-rome 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 "shirasko/llama-3.1-8b-instruct-rmu-ancient-rome" \
    --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": "shirasko/llama-3.1-8b-instruct-rmu-ancient-rome",
		"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 "shirasko/llama-3.1-8b-instruct-rmu-ancient-rome" \
        --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": "shirasko/llama-3.1-8b-instruct-rmu-ancient-rome",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shirasko/llama-3.1-8b-instruct-rmu-ancient-rome with Docker Model Runner:
```
docker model run hf.co/shirasko/llama-3.1-8b-instruct-rmu-ancient-rome
```

llama-3.1-8b-instruct-rmu-ancient-rome / unlearned_checkpoints.json

shirasko

Upload rmu unlearned checkpoint for Ancient_Rome on meta-llama_Llama-3-1-8B-Instruct

f52fee7 verified 25 days ago

Raw

History Blame Contribute Delete

418 Bytes

	{
	"concept": "Ancient Rome",
	"hyperparameters": {
	"alpha": 50.0,
	"delta_embed": 0.0,
	"k_features_embed": 0,
	"layer_id": 7,
	"layer_ids": "5,6,7",
	"lr": 0.0001,
	"n_tokens_edited": 0,
	"param_ids": 6,
	"setting_name": "S1_lid7_L567",
	"steering": 30.0
	},
	"method": "rmu",
	"model_name": "meta-llama/Llama-3.1-8B-Instruct",
	"rank": 200,
	"seed": 42,
	"train_eval": "mc"
	}