Instructions to use MrPibb/KillChain-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MrPibb/KillChain-8B with Transformers:

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

pipe = pipeline("text-generation", model="MrPibb/KillChain-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MrPibb/KillChain-8B")
model = AutoModelForCausalLM.from_pretrained("MrPibb/KillChain-8B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MrPibb/KillChain-8B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MrPibb/KillChain-8B

SGLang

How to use MrPibb/KillChain-8B 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 "MrPibb/KillChain-8B" \
    --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": "MrPibb/KillChain-8B",
		"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 "MrPibb/KillChain-8B" \
        --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": "MrPibb/KillChain-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MrPibb/KillChain-8B with Docker Model Runner:
```
docker model run hf.co/MrPibb/KillChain-8B
```

KillChain-8B

File size: 6,185 Bytes

aca4981


tokenizer.json:   0%|                                                                                                  | 0.00/11.4M [00:00<?, ?B/s]
tokenizer.json:  27%|████████████████████████▎                                                                | 3.12M/11.4M [00:00<00:00, 11.5MB/s]
tokenizer.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 11.4M/11.4M [00:00<00:00, 32.5MB/s]
[2026-01-05 19:56:22,639] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:444] Loading raw datasets...
[2026-01-05 19:56:23,255] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:444] Loading dataset: WNT3D/Ultimate-Offensive-Red-Team with base_type: alpaca and prompt_style: None

Dropping Long Sequences (>4096) (num_proc=4):   0%|                                                               | 0/25620 [00:00<?, ? examples/s]
Dropping Long Sequences (>4096) (num_proc=4):   4%|█▉                                                | 1000/25620 [00:00<00:05, 4469.12 examples/s]
Dropping Long Sequences (>4096) (num_proc=4):  23%|███████████▍                                     | 6000/25620 [00:00<00:00, 21720.64 examples/s]
Dropping Long Sequences (>4096) (num_proc=4):  43%|████████████████████▌                           | 11000/25620 [00:00<00:00, 31422.54 examples/s]
Dropping Long Sequences (>4096) (num_proc=4):  66%|███████████████████████████████▊                | 17000/25620 [00:00<00:00, 34083.34 examples/s]
Dropping Long Sequences (>4096) (num_proc=4):  86%|█████████████████████████████████████████▏      | 22000/25620 [00:00<00:00, 38301.21 examples/s]
Dropping Long Sequences (>4096) (num_proc=4): 100%|████████████████████████████████████████████████| 25620/25620 [00:00<00:00, 29329.19 examples/s]

Saving the dataset (0/4 shards):   0%|                                                                            | 0/25103 [00:00<?, ? examples/s]
Saving the dataset (0/4 shards):  16%|█████████▉                                                    | 4000/25103 [00:00<00:00, 22838.14 examples/s]
Saving the dataset (1/4 shards): 100%|█████████████████████████████████████████████████████████████| 25103/25103 [00:00<00:00, 22838.14 examples/s]
Saving the dataset (2/4 shards): 100%|█████████████████████████████████████████████████████████████| 25103/25103 [00:00<00:00, 22838.14 examples/s]
Saving the dataset (3/4 shards): 100%|█████████████████████████████████████████████████████████████| 25103/25103 [00:00<00:00, 22838.14 examples/s]
Saving the dataset (4/4 shards): 100%|█████████████████████████████████████████████████████████████| 25103/25103 [00:00<00:00, 22838.14 examples/s]
Saving the dataset (4/4 shards): 100%|█████████████████████████████████████████████████████████████| 25103/25103 [00:00<00:00, 81840.32 examples/s]

Loading checkpoint shards:   0%|                                                                                             | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards:  20%|█████████████████                                                                    | 1/5 [00:00<00:03,  1.04it/s]
Loading checkpoint shards:  40%|██████████████████████████████████                                                   | 2/5 [00:02<00:03,  1.13s/it]
Loading checkpoint shards:  60%|███████████████████████████████████████████████████                                  | 3/5 [00:03<00:02,  1.16s/it]
Loading checkpoint shards:  80%|████████████████████████████████████████████████████████████████████                 | 4/5 [00:04<00:01,  1.00s/it]
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:04<00:00,  1.32it/s]
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:04<00:00,  1.11it/s]

generation_config.json:   0%|                                                                                            | 0.00/239 [00:00<?, ?B/s]
generation_config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████| 239/239 [00:00<00:00, 435kB/s]