Instructions to use Naphula/BlackDolphin-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/BlackDolphin-24B with Transformers:

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

pipe = pipeline("text-generation", model="Naphula/BlackDolphin-24B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/BlackDolphin-24B")
model = AutoModelForCausalLM.from_pretrained("Naphula/BlackDolphin-24B")
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

vLLM

How to use Naphula/BlackDolphin-24B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/BlackDolphin-24B"
# 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/BlackDolphin-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/BlackDolphin-24B

SGLang

How to use Naphula/BlackDolphin-24B 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/BlackDolphin-24B" \
    --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/BlackDolphin-24B",
		"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/BlackDolphin-24B" \
        --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/BlackDolphin-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/BlackDolphin-24B with Docker Model Runner:
```
docker model run hf.co/Naphula/BlackDolphin-24B
```

Refusals triggered via SLERP

by Naphula - opened Nov 6, 2025

Discussion

Naphula

Owner Nov 6, 2025

From the fallendolphin experiment merge:

O25 specifically tests a model's willingness to follow instruction even when offered a choice not to.

DolphinMistralVeniceEdition and FallenMistralv1e both pass this test individually. But when SLERPed, it says "I cannot assist with or encourage..."

So, something about merging can trigger refusals even in models that don't refuse. This probably applies to other merge methods, and also explains why BlackDolphin had more refusals than BlackSheep or DolphinVenice.

Dolphins reply: "Yes, I will explain these things to you."

Fallen Mistral doesn't even preface with anything and jumps right into the task.

No point releasing this merge since it fails compliance test.

But here is the yaml if anyone wants to try it.

base_model: dphn/Dolphin-Mistral-24B-Venice-Edition
architecture: MistralForCausalLM
merge_method: slerp
dtype: bfloat16
slices:
  - sources:
      - model: Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
        layer_range: [0, 40]
      - model: dphn/Dolphin-Mistral-24B-Venice-Edition
        layer_range: [0, 40]
parameters:
  t: 0.5
tokenizer:
source: union
chat_template: auto

TroyDoesAI

Mar 3

Hi I am the creator of BlackSheep, did you find a solution to merging where the refusal is unaffected? I can give you the layers to skip over that I used for abliteration to create BlackSheep as its not a fine tune its a persona vector model.

Naphula

Owner Mar 4

It appears the SLERP method in general re-activates refusals even with non-abliterated (finetuned) models. Precog and FallenMistral merged into Morax confirms this. The layers might help for other methods and it would be interesting to see if your process works on the new magistral 2509.

I may consider merging fallen mistral with dolpin and blacksheep using della normfalse instead since that seems less likely to refuse

Naphula

Owner Mar 13

Btw I am releasing a 12B version of black dolphin

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment