Instructions to use InferenceIllusionist/Magic-Dolphin-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InferenceIllusionist/Magic-Dolphin-7b with Transformers:

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

pipe = pipeline("text-generation", model="InferenceIllusionist/Magic-Dolphin-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("InferenceIllusionist/Magic-Dolphin-7b")
model = AutoModelForCausalLM.from_pretrained("InferenceIllusionist/Magic-Dolphin-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use InferenceIllusionist/Magic-Dolphin-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InferenceIllusionist/Magic-Dolphin-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InferenceIllusionist/Magic-Dolphin-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/InferenceIllusionist/Magic-Dolphin-7b

SGLang

How to use InferenceIllusionist/Magic-Dolphin-7b 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 "InferenceIllusionist/Magic-Dolphin-7b" \
    --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": "InferenceIllusionist/Magic-Dolphin-7b",
		"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 "InferenceIllusionist/Magic-Dolphin-7b" \
        --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": "InferenceIllusionist/Magic-Dolphin-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use InferenceIllusionist/Magic-Dolphin-7b with Docker Model Runner:
```
docker model run hf.co/InferenceIllusionist/Magic-Dolphin-7b
```

InferenceIllusionist commited on Jul 16, 2024

Commit

7f7aed9

verified ·

1 Parent(s): bd0d487

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -118,7 +118,7 @@ model-index:
 <b>The follow-up to this model has been released, check out the updated benchmarks here for [Excalibur-7b](https://huggingface.co/InferenceIllusionist/Excalibur-7b)</b>
-For GGUF files please look [here](https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b-GGUF)
 A linear merge of:
 - [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)

 <b>The follow-up to this model has been released, check out the updated benchmarks here for [Excalibur-7b](https://huggingface.co/InferenceIllusionist/Excalibur-7b)</b>
+A full suite of GGUF quantizations can be found [here](https://huggingface.co/RichardErkhov/InferenceIllusionist_-_Magic-Dolphin-7b-gguf), courtesy of [RichardErkhov](https://huggingface.co/RichardErkhov/)
 A linear merge of:
 - [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)