Instructions to use dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B with Transformers:

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

pipe = pipeline("text-generation", model="dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B")
model = AutoModelForCausalLM.from_pretrained("dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B")
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 dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B"
# 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-2.9.1-Phi-3-Kensho-4.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B

SGLang

How to use dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B 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-2.9.1-Phi-3-Kensho-4.5B" \
    --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-2.9.1-Phi-3-Kensho-4.5B",
		"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-2.9.1-Phi-3-Kensho-4.5B" \
        --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-2.9.1-Phi-3-Kensho-4.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B with Docker Model Runner:
```
docker model run hf.co/dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Dolphin 2.9.1 Phi-3 Kensho 4.5b 🐬

Curated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations

Discord: https://discord.gg/cognitivecomputations

Our appreciation for the sponsors of Dolphin 2.9:

Crusoe Cloud - provided excellent on-demand 8xL40Snode

This model utilizes PEFT layer replication at inference time to duplicate layers and increase parameter count. This works with both the merged model that comes stock with this repository, and the adapter that is attached as well. Performance will be similar with both methods, but VRAM use is considerably less when using the adapter. This model was initialized using Unsloth's Mistralfied Phi-3-Instruct-4k. If you choose to use the adapter method, please attach it to their model.

This model is based on Phi-3-Mini-Instruct-4k, and is governed by the MIT license in which Microsoft released Phi-3.

The base model has 4k context, and the qLoRA fine-tuning was with 4k sequence length.

It took 2.5 days on 8xL40S node provided by Crusoe Cloud

This model uses ChatML prompt template format.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Dolphin-2.9.1 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

Dolphin is licensed according to the MIT license. I grant permission for any use, including commercial. Dolphin was trained on data generated from GPT4, among other models.

Downloads last month: 301

Model tree for dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B

Base model

unsloth/Phi-3-mini-4k-instruct

Finetuned

(48)

this model

Finetunes

1 model

Quantizations

2 models

dphn
/

Dolphin-2.9.1-Phi-3-Kensho-4.5B

Dolphin 2.9.1 Phi-3 Kensho 4.5b 🐬

Model tree for dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B

Datasets used to train dphn/Dolphin-2.9.1-Phi-3-Kensho-4.5B