Instructions to use dphn/Dolphin3.0-Mistral-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dphn/Dolphin3.0-Mistral-24B with Transformers:

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

pipe = pipeline("text-generation", model="dphn/Dolphin3.0-Mistral-24B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dphn/Dolphin3.0-Mistral-24B")
model = AutoModelForCausalLM.from_pretrained("dphn/Dolphin3.0-Mistral-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dphn/Dolphin3.0-Mistral-24B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dphn/Dolphin3.0-Mistral-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": "dphn/Dolphin3.0-Mistral-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dphn/Dolphin3.0-Mistral-24B

SGLang

How to use dphn/Dolphin3.0-Mistral-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 "dphn/Dolphin3.0-Mistral-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": "dphn/Dolphin3.0-Mistral-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 "dphn/Dolphin3.0-Mistral-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": "dphn/Dolphin3.0-Mistral-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dphn/Dolphin3.0-Mistral-24B with Docker Model Runner:
```
docker model run hf.co/dphn/Dolphin3.0-Mistral-24B
```

the egg + yolk test

by hbanaharis - opened Feb 8, 2025

Discussion

hbanaharis

Feb 8, 2025

there are 6 eggs. of these one has a double yolk and another is missing a yolk. how many yolks in total?

Let's break it down:

Typical Eggs: Normally, each egg has 1 yolk. So for 4 regular eggs: (4 \times 1 = 4) yolks.
Double Yolk Egg: Adds 1 extra yolk (now 5 total).
Missing Yolk Egg: Subtracts 1 yolk (now 4 total).

Total Yolks: (4 + 1 - 1 = 4).

Answer: There are 4 yolks in total.

Now when I use the same prompt in deepseek-r1:32b (quant 4)

there are 6 eggs. of these one has a double yolk and another is missing a yolk. how many yolks in total?

To determine the total number of yolks, let's break down each egg:

Normal Eggs: There are 4 normal eggs. Each of these typically contains 1 yolk.
- Total yolks from normal eggs: 4 × 1 = 4
Double Yolk Egg: One egg has a double yolk, which means it contains 2 yolks.
- Total yolks from the double yolk egg: 2
Missing Yolk Egg: Another egg is missing its yolk, so it contributes 0 yolks.
- Total yolks from the missing yolk egg: 0

Now, summing up all the yolks:
4 (from normal eggs) + 2 (double yolk) + 0 (missing yolk) = 6

Therefore, there are a total of 6 yolks.

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