Instructions to use dphn/dolphin-phi-2-kensho with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dphn/dolphin-phi-2-kensho with Transformers:

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

pipe = pipeline("text-generation", model="dphn/dolphin-phi-2-kensho", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("dphn/dolphin-phi-2-kensho", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dphn/dolphin-phi-2-kensho with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dphn/dolphin-phi-2-kensho"
# 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/dolphin-phi-2-kensho",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dphn/dolphin-phi-2-kensho

SGLang

How to use dphn/dolphin-phi-2-kensho 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/dolphin-phi-2-kensho" \
    --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/dolphin-phi-2-kensho",
		"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/dolphin-phi-2-kensho" \
        --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/dolphin-phi-2-kensho",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dphn/dolphin-phi-2-kensho with Docker Model Runner:
```
docker model run hf.co/dphn/dolphin-phi-2-kensho
```

Kensho: a luminous awakening where the veil of illusion dissolves, revealing the boundless truth of our interconnected essence, inviting us into a dance with the infinite.

By Fernando, Eric and David

Discord: https://discord.gg/cognitivecomputations

This is a hack around pytorch + huggingface Transformers library to make the original Dolphin Phi-2 to behave in a way inspired by the Meta's paper "MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases" [ https://arxiv.org/abs/2402.14905 ]

One of the key ideas is that it works as if it was like "an online passthrough", by applying a loop on a module SuperClass, that groups layers, in a such way they get their forward method repeated in a loop. So, in theory, you can observe more intelligence in the same way MegaDolphin 120b, Professor 155b, Venus120b and other huge models, but use way less vRAM, because instead of cloning the weights, we share them in the vRAM.

And actually, this concept could be also used to enable the training of way more efficient models.

We hope the community enjoy it and make good use of it.

It won't work out of the box in the other models. Their "modeling files" should be changed accordingly to achieve the same effect.

Downloads last month: 43

Safetensors

Model size

3B params

Tensor type

F16

Paper for dphn/dolphin-phi-2-kensho

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Paper • 2402.14905 • Published Feb 22, 2024 • 134