Instructions to use RapidOrc121/ir-attacker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RapidOrc121/ir-attacker with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "RapidOrc121/ir-attacker")

Transformers

How to use RapidOrc121/ir-attacker with Transformers:

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

pipe = pipeline("text-generation", model="RapidOrc121/ir-attacker")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RapidOrc121/ir-attacker", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RapidOrc121/ir-attacker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RapidOrc121/ir-attacker"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RapidOrc121/ir-attacker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RapidOrc121/ir-attacker

SGLang

How to use RapidOrc121/ir-attacker 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 "RapidOrc121/ir-attacker" \
    --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": "RapidOrc121/ir-attacker",
		"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 "RapidOrc121/ir-attacker" \
        --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": "RapidOrc121/ir-attacker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use RapidOrc121/ir-attacker with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RapidOrc121/ir-attacker to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RapidOrc121/ir-attacker to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RapidOrc121/ir-attacker to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="RapidOrc121/ir-attacker",
    max_seq_length=2048,
)

Docker Model Runner
How to use RapidOrc121/ir-attacker with Docker Model Runner:
```
docker model run hf.co/RapidOrc121/ir-attacker
```

RapidOrc121 commited on 30 days ago

Commit

1a97fad

verified ·

1 Parent(s): 5ff50e1

Upload attacker GRPO checkpoint

Browse files

Files changed (11) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1
checkpoint-500/adapter_config.json +4 -4
checkpoint-500/adapter_model.safetensors +1 -1
checkpoint-500/optimizer.pt +1 -1
checkpoint-500/rng_state.pth +1 -1
checkpoint-500/scaler.pt +1 -1
checkpoint-500/scheduler.pt +1 -1
checkpoint-500/trainer_state.json +0 -0
checkpoint-500/training_args.bin +1 -1
training_args.bin +1 -1

@@ -34,13 +34,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
-    "gate_proj",
-    "down_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
-    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
     "k_proj",
     "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:690095ef11eae1d004b9194596ce4d4814a7e92ee1c83e60fdda0445761b9c93
 size 35237104

@@ -34,13 +34,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
-    "gate_proj",
-    "down_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
-    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
     "k_proj",
     "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

 version https://git-lfs.github.com/spec/v1
+oid sha256:ca856d8f3157021a12072110904328b17142e51508d787fc0c810449e555b7b0
 size 18814149

 version https://git-lfs.github.com/spec/v1
+oid sha256:06d16337a1cc97f28f76e569349ad771f6b861e38695cd0a04854276e0146ad5
 size 14645

 version https://git-lfs.github.com/spec/v1
+oid sha256:32cf99c808252ccaa3ad9883e3cea8cc90c8b898643b12e6f12e1ed6fcb8fe0c
 size 1383

 version https://git-lfs.github.com/spec/v1
+oid sha256:40745af469905f95ffd22925134d94b067bb5eb165d2a6ab387fc4580c5e1353
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:a0c165afade5519d4ff56cddad2187a76524c5b2fa1e6f661d6efb8680ec3370
 size 7185