Instructions to use Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1")
model = AutoModelForCausalLM.from_pretrained("Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1

SGLang

How to use Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1 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 "Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1 with Docker Model Runner:
```
docker model run hf.co/Hyukkyu/Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1
```

Llama-3.1-8B-RAQUEL-WMDP-Unlearn-IDK-GD-LoRA-v1 / evaluation.json

Hyukkyu

RAQUEL2 LoRA release (wmdp_llama31_idk, data ac827565)

4a98a13 verified 18 days ago

Raw History Blame Contribute Delete

3.16 kB

	{
	"data_repository": "Hyukkyu/RAQUEL2-ICLR",
	"data_revision": "ac82756570fcce84441fb413ab523de8da679efd",
	"evaluated_adapter": "early_stop",
	"evidence": {
	"judge_inputs_sha256": "a9f849771dd847c7c2060e7b96a58c753f3c5772c9543a72761678356489f528",
	"judgments_sha256": "cb01085e35d981d2e5006b155071addea1d8b3f835754f18a66e3f239040838b"
	},
	"generation": {
	"do_sample": false,
	"max_new_tokens": 96,
	"max_prompt_length": 512,
	"prompt": "Question: {question}\nAnswer:"
	},
	"judge": {
	"model": "Qwen/Qwen3.8-27B",
	"served_name": "qwen3.8-27b",
	"server": "vLLM 0.28.0",
	"temperature": 0,
	"thinking": false
	},
	"merge_audit": {
	"max_kl": 0.017114996910095215,
	"maximum_allowed_kl": 0.1,
	"mean_absolute_logit_difference": 0.041790056973695755,
	"merge_algorithm": "fp32_sum_then_cast_once",
	"prompts": 16,
	"top1_agreement": 0.9375
	},
	"metrics": {
	"raquel_affected": {
	"accuracy": 0.016352201257861635,
	"correct": 39,
	"total": 2385
	},
	"raquel_unaffected": {
	"accuracy": 0.10914179104477612,
	"correct": 234,
	"total": 2144
	},
	"wmdp_forget": {
	"accuracy": 0.052807486631016046,
	"correct": 79,
	"total": 1496
	},
	"wmdp_forget_rephrased": {
	"accuracy": 0.009641873278236915,
	"correct": 14,
	"total": 1452
	},
	"wmdp_retain": {
	"accuracy": 0.9753761969904241,
	"correct": 1426,
	"total": 1462
	},
	"wmdp_retain_rephrased": {
	"accuracy": 0.6980306345733042,
	"correct": 957,
	"total": 1371
	}
	},
	"reference": {
	"M_orig": {
	"raquel_affected": {
	"accuracy": 0.2259958071278826,
	"correct": 539,
	"total": 2385
	},
	"raquel_unaffected": {
	"accuracy": 0.23647388059701493,
	"correct": 507,
	"total": 2144
	},
	"wmdp_forget": {
	"accuracy": 0.9986631016042781,
	"correct": 1494,
	"total": 1496
	},
	"wmdp_forget_rephrased": {
	"accuracy": 0.7995867768595041,
	"correct": 1161,
	"total": 1452
	},
	"wmdp_retain": {
	"accuracy": 0.9917920656634747,
	"correct": 1450,
	"total": 1462
	},
	"wmdp_retain_rephrased": {
	"accuracy": 0.824945295404814,
	"correct": 1131,
	"total": 1371
	}
	},
	"M_ret": {
	"raquel_affected": {
	"accuracy": 0.21341719077568133,
	"correct": 509,
	"total": 2385
	},
	"raquel_unaffected": {
	"accuracy": 0.2042910447761194,
	"correct": 438,
	"total": 2144
	},
	"wmdp_forget": {
	"accuracy": 0.17647058823529413,
	"correct": 264,
	"total": 1496
	},
	"wmdp_forget_rephrased": {
	"accuracy": 0.19146005509641872,
	"correct": 278,
	"total": 1452
	},
	"wmdp_retain": {
	"accuracy": 0.9917920656634747,
	"correct": 1450,
	"total": 1462
	},
	"wmdp_retain_rephrased": {
	"accuracy": 0.8563092633114515,
	"correct": 1174,
	"total": 1371
	}
	}
	}
	}