Instructions to use dphn/dolphin-2.9.1-llama-3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dphn/dolphin-2.9.1-llama-3-8b with Transformers:

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

pipe = pipeline("text-generation", model="dphn/dolphin-2.9.1-llama-3-8b")
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-llama-3-8b")
model = AutoModelForCausalLM.from_pretrained("dphn/dolphin-2.9.1-llama-3-8b")
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 Settings

vLLM

How to use dphn/dolphin-2.9.1-llama-3-8b 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-llama-3-8b"
# 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-llama-3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dphn/dolphin-2.9.1-llama-3-8b

SGLang

How to use dphn/dolphin-2.9.1-llama-3-8b 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-llama-3-8b" \
    --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-llama-3-8b",
		"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-llama-3-8b" \
        --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-llama-3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dphn/dolphin-2.9.1-llama-3-8b with Docker Model Runner:
```
docker model run hf.co/dphn/dolphin-2.9.1-llama-3-8b
```

GGUF Models struggle with ChatML format in LMStudio for me

by tculler91 - opened May 13, 2024

Discussion

tculler91

May 13, 2024

•

edited May 13, 2024

Just curious if anyone else is experiencing issues using ChatML format with this model?

Despite updating LMStudio and trying out different gguf uploads, this model in 8-bit GGUF is generating random nonsense in ChatML mode.
For me, it will only generate normal text if you switch to Llama-3 format.

The same settings and ChatML format work fine when switching to Hermes 2 Pro though, which makes me wonder if this is a bug?
This is the first time I've experienced this with a Dolphin model.

Crystalcareai

May 13, 2024

Yeah we're investigating this. You can use the original llama-3 template in LM-studio for now.

saishf

May 20, 2024

Just curious if anyone else is experiencing issues using ChatML format with this model?

Despite updating LMStudio and trying out different gguf uploads, this model in 8-bit GGUF is generating random nonsense in ChatML mode.
For me, it will only generate normal text if you switch to Llama-3 format.

The same settings and ChatML format work fine when switching to Hermes 2 Pro though, which makes me wonder if this is a bug?
This is the first time I've experienced this with a Dolphin model.

It seems to be affecting more than just this model, a few other models i've tried trained that are on ChatML can't do so once quantized down but do fine in bf16. New model quirks 😶‍🌫️

Kearm

May 20, 2024

Just curious if anyone else is experiencing issues using ChatML format with this model?

Despite updating LMStudio and trying out different gguf uploads, this model in 8-bit GGUF is generating random nonsense in ChatML mode.
For me, it will only generate normal text if you switch to Llama-3 format.

The same settings and ChatML format work fine when switching to Hermes 2 Pro though, which makes me wonder if this is a bug?
This is the first time I've experienced this with a Dolphin model.

It seems to be affecting more than just this model, a few other models i've tried trained that are on ChatML can't do so once quantized down but do fine in bf16. New model quirks 😶‍🌫️

@saishf I concur.

Kearm changed discussion status to closed May 20, 2024

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