Instructions to use Naphula/Warlock-7B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Warlock-7B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Naphula/Warlock-7B-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/Warlock-7B-v2")
model = AutoModelForMultimodalLM.from_pretrained("Naphula/Warlock-7B-v2")
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 Naphula/Warlock-7B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Warlock-7B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Warlock-7B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/Warlock-7B-v2

SGLang

How to use Naphula/Warlock-7B-v2 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 "Naphula/Warlock-7B-v2" \
    --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": "Naphula/Warlock-7B-v2",
		"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 "Naphula/Warlock-7B-v2" \
        --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": "Naphula/Warlock-7B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/Warlock-7B-v2 with Docker Model Runner:
```
docker model run hf.co/Naphula/Warlock-7B-v2
```

Naphula commited on Nov 6, 2025

Commit

80727db

verified ·

1 Parent(s): 8769ec0

Upload Warlock-7B-v2-Q8_K_XL.txt

Browse files

Files changed (1) hide show

Warlock-7B-v2-Q8_K_XL.txt +1 -0

Warlock-7B-v2-Q8_K_XL.txt ADDED Viewed

	@@ -0,0 +1 @@

+ llama-quantize --tensor-type output.weight=F16 --tensor-type token_embd.weight=F16 --tensor-type "blk\.(0|1|2|30|31)\.attn_k.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.attn_k.weight=Q8_0" --tensor-type "blk\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31)\.attn_output.weight=Q8_0" --tensor-type "blk\.(0|1|2|30|31)\.attn_q.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.attn_q.weight=Q8_0" --tensor-type "blk\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31)\.attn_v.weight=F16" --tensor-type "blk\.(0|1|2|30|31)\.ffn_down.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.ffn_down.weight=Q8_0" --tensor-type "blk\.(0|1|2|30|31)\.ffn_gate.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.ffn_gate.weight=Q8_0" --tensor-type "blk\.(0|1|2|30|31)\.ffn_up.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.ffn_up.weight=Q8_0" C:\Quanter\outputs\input.gguf C:\Quanter\outputs\output.gguf Q8_0