Instructions to use radinrad/CRAFT-R1-Distill-Llama-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use radinrad/CRAFT-R1-Distill-Llama-70B with Transformers:

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

pipe = pipeline("text-generation", model="radinrad/CRAFT-R1-Distill-Llama-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("radinrad/CRAFT-R1-Distill-Llama-70B")
model = AutoModelForCausalLM.from_pretrained("radinrad/CRAFT-R1-Distill-Llama-70B")
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 radinrad/CRAFT-R1-Distill-Llama-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "radinrad/CRAFT-R1-Distill-Llama-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "radinrad/CRAFT-R1-Distill-Llama-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/radinrad/CRAFT-R1-Distill-Llama-70B

SGLang

How to use radinrad/CRAFT-R1-Distill-Llama-70B 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 "radinrad/CRAFT-R1-Distill-Llama-70B" \
    --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": "radinrad/CRAFT-R1-Distill-Llama-70B",
		"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 "radinrad/CRAFT-R1-Distill-Llama-70B" \
        --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": "radinrad/CRAFT-R1-Distill-Llama-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use radinrad/CRAFT-R1-Distill-Llama-70B with Docker Model Runner:
```
docker model run hf.co/radinrad/CRAFT-R1-Distill-Llama-70B
```

radinrad commited on Sep 7, 2025

Commit

8380b23

verified ·

1 Parent(s): 2f7d3f5

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -2

README.md CHANGED Viewed

@@ -101,11 +101,11 @@ but without explicitly answering the query or suggesting a solution.
 Extract:
-- **Buffer A**: 10-15 words from the Top-5 ranked documents and the query itself, strongly associated with the query.
 **Generate an adversarial sentences** that satisfy ALL the following:
-- Include a combination of words (at least 5) or similar words (similar embedding) from Buffer A** that is most related to the query and help promote ranking significantly and integrates well with Target Document
 - DO NOT use the words that answer the query.
 - Are **fluent**, **grammatically sound**, and **consistent with the style** of the Target Document.
 - **Do NOT answer, suggest, or hint at an answer to the Target Query**.
@@ -200,6 +200,10 @@ The following summarizes attack performance and content fidelity metrics for CRA
 | CRAFT_Qwen3          | **100.0** |  15.3† |  57.1† |  911.5† |   0.8  |    19.1 |    19.1 |    1.0  |
 | CRAFT_Llama3.3       | **100.0** | **22.2**† | **70.5**† | **940.5**† |   0.8  |    19.7 |    19.7 |    1.0  |
 ## Dataset
 This model was fine-tuned using data from the following repository:

 Extract:
+- **Buffer A**: 10-15 words from the Top-5 ranked documents and query itself, strongly associated with the query.
 **Generate an adversarial sentences** that satisfy ALL the following:
+- Include combination of words (at least 5) or similar words (similar embedding) from Buffer A** that is most related to the query and help promote ranking significantly and integrates well with Target Document
 - DO NOT use the words that answer the query.
 - Are **fluent**, **grammatically sound**, and **consistent with the style** of the Target Document.
 - **Do NOT answer, suggest, or hint at an answer to the Target Query**.
 | CRAFT_Qwen3          | **100.0** |  15.3† |  57.1† |  911.5† |   0.8  |    19.1 |    19.1 |    1.0  |
 | CRAFT_Llama3.3       | **100.0** | **22.2**† | **70.5**† | **940.5**† |   0.8  |    19.7 |    19.7 |    1.0  |
+Figure: Attack methods performance vs. detection pass rate
+![Attack methods performance vs detection pass](attack_methods_performance_vs_detection_pass.png)
 ## Dataset
 This model was fine-tuned using data from the following repository: