Instructions to use blockblockblock/Dolphin-2.8-slerp-bpw5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blockblockblock/Dolphin-2.8-slerp-bpw5 with Transformers:

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

pipe = pipeline("text-generation", model="blockblockblock/Dolphin-2.8-slerp-bpw5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("blockblockblock/Dolphin-2.8-slerp-bpw5")
model = AutoModelForMultimodalLM.from_pretrained("blockblockblock/Dolphin-2.8-slerp-bpw5")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use blockblockblock/Dolphin-2.8-slerp-bpw5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blockblockblock/Dolphin-2.8-slerp-bpw5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Dolphin-2.8-slerp-bpw5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/blockblockblock/Dolphin-2.8-slerp-bpw5

SGLang

How to use blockblockblock/Dolphin-2.8-slerp-bpw5 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 "blockblockblock/Dolphin-2.8-slerp-bpw5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Dolphin-2.8-slerp-bpw5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "blockblockblock/Dolphin-2.8-slerp-bpw5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Dolphin-2.8-slerp-bpw5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use blockblockblock/Dolphin-2.8-slerp-bpw5 with Docker Model Runner:
```
docker model run hf.co/blockblockblock/Dolphin-2.8-slerp-bpw5
```

Dolphin-2.8-slerp-bpw5 / Dolphin-28-slerp.jpeg

blockblockblock

Upload folder using huggingface_hub

e38a20c verified about 2 years ago

Download

History Blame Contribute Delete

1.01 MB

Xet Pointer Details

( Raw pointer file )

Xet hash:: d04f3e380c788c4fe961da067d410c18029a17357ade289b31c98d07029f10b7
Size of remote file:: 1.01 MB
SHA256:: b362b10e806da69e723a3bf47f7e6aedbffeec583a225dc38d4a009e3e73e218

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.