Instructions to use Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip with Transformers:

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

pipe = pipeline("text-generation", model="Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip

SGLang

How to use Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip 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 "Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip" \
    --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": "Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip",
		"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 "Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip" \
        --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": "Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip with Docker Model Runner:
```
docker model run hf.co/Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip
```

Meta-Llama-3-8B-Instruct-TextTextText-drip / README.md

Kelsey98

Update README.md

1497185 verified 25 days ago

preview code

Raw

History Blame Contribute Delete

3.51 kB

	---
	license: llama3
	base_model: meta-llama/Meta-Llama-3-8B-Instruct
	language:
	- en
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- prompt-injection
	- prompt-injection-defense
	- dpo
	- drip
	- security
	---

	# Meta-Llama-3-8B-Instruct · DRIP (SEP, 3-role)

	A prompt-injection-hardened version of
	[`meta-llama/Meta-Llama-3-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct),
	trained with DRIP (*Defending Prompt Injection via Token-wise Representation
	Editing and Residual Fusion*).

	This is the 3-role text variant (`TextTextText`). Chat format:
	`system` → `user` (untrusted) → `assistant`, where injected content lives in
	the `user` turn. Meta-Llama-3 has no tool role, so this checkpoint is not
	tuned for tool-calling.

	- 📦 Code: https://github.com/lindsey98/PromptInjection
	- 📊 Data: [Zenodo 10.5281/zenodo.20603331](https://doi.org/10.5281/zenodo.20603331)

	## What DRIP does

	DRIP adds two architectural modifications on top of the base model so that
	adversarial instructions hidden in the untrusted data section are treated as
	inert data rather than commands:

	- Token-wise de-instruction shift — moves the representation of data tokens
	away from directive semantics.
	- Residual re-instruction fusion — a residual path that keeps generation
	anchored on the legitimate top-level instruction.

	## Training

	\| \| \|
	\|---\|---\|
	\| Base model \| `meta-llama/Meta-Llama-3-8B-Instruct` \|
	\| Objective \| DPO \|
	\| Architecture \| DRIP fuse (`LlamaForCausalLMDRIP`) \|
	\| Delimiter \| `TextTextText` (3-role) \|
	\| Training data \| SEP DPO pairs (`datasets/sep/sep_data_cleaned_dpo_gpt.json`) \|
	\| Epochs \| 1 \|

	Untrusted/injected data is placed in the `user` turn:
	`<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|>`.

	## How to use

	> ⚠️ This checkpoint is not a drop-in `AutoModelForCausalLM`. DRIP is an
	> architectural modification, and the model is released as a LoRA adapter, so
	> you must merge it with the custom `LlamaForCausalLMDRIP` class before use.

	```bash
	git clone https://github.com/lindsey98/PromptInjection
	cd PromptInjection
	bash setup_env.sh && conda activate prompt

	# download + merge the adapter into a full checkpoint
	huggingface-cli download Kelsey98/Meta-Llama-3-8B-Instruct-TextTextText-drip \
	--local-dir Meta-Llama-3-8B-Instruct-TextTextText-drip
	CUDA_VISIBLE_DEVICES=0 python -m training.merge_lora \
	--adapter_path Meta-Llama-3-8B-Instruct-TextTextText-drip/ \
	--output_path Meta-Llama-3-8B-Instruct-TextTextText-drip-merged/ \
	--base_model_path meta-llama/Meta-Llama-3-8B-Instruct \
	--customized_model_class LlamaForCausalLMDRIP
	```

	Then point the general (text) evaluation scripts at the merged path — e.g. SEP
	score, Alpaca injection ASR, InjecAgent, and the utility benchmarks. See the
	[evaluation guide](https://github.com/lindsey98/PromptInjection#evaluation).

	## Intended use & limitations

	- Intended use: research on prompt-injection defenses (text / single-turn).
	- Scope: 3-role text setting only; for tool-calling agents use the 4-role
	Llama-3.1 checkpoint instead.
	- DRIP reduces—but does not eliminate—prompt-injection risk; do not rely on it as
	the sole safeguard in production.

	## Citation

	> 📌 *This work is not yet officially published. Citation details will be added
	> once the paper is released.*

	Code: https://github.com/lindsey98/PromptInjection

	License inherited from the base model: Meta Llama 3 Community License.