Instructions to use NECOUDBFM/Jellyfish-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NECOUDBFM/Jellyfish-13B with Transformers:

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

pipe = pipeline("text-generation", model="NECOUDBFM/Jellyfish-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NECOUDBFM/Jellyfish-13B")
model = AutoModelForCausalLM.from_pretrained("NECOUDBFM/Jellyfish-13B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NECOUDBFM/Jellyfish-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NECOUDBFM/Jellyfish-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NECOUDBFM/Jellyfish-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NECOUDBFM/Jellyfish-13B

SGLang

How to use NECOUDBFM/Jellyfish-13B 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 "NECOUDBFM/Jellyfish-13B" \
    --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": "NECOUDBFM/Jellyfish-13B",
		"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 "NECOUDBFM/Jellyfish-13B" \
        --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": "NECOUDBFM/Jellyfish-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NECOUDBFM/Jellyfish-13B with Docker Model Runner:
```
docker model run hf.co/NECOUDBFM/Jellyfish-13B
```

HCZhang commited on Dec 11, 2023

Commit

33e7aa1

1 Parent(s): a5cca90

update jellyfish to v1.1

Browse files

Files changed (3) hide show

pytorch_model-00001-of-00003.bin +3 -0
pytorch_model-00002-of-00003.bin +3 -0
pytorch_model-00003-of-00003.bin +3 -0

pytorch_model-00001-of-00003.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fc10729079e005071864e8f2ee07cc1a6b974e67cd03dc57b54e9ce080c7613b
+size 9948739913

pytorch_model-00002-of-00003.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6f8e2d0dd2d5ee9d9c89b101298983640376af7025f7c1da82cb179c45f9dc
+size 9904155408

pytorch_model-00003-of-00003.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08ec192e2b887cffdcdd165e237c088864f5035b841cf0013c079c2efa7d7eed
+size 6178998687