Instructions to use hflog/jondurbin-bagel-7b-v0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hflog/jondurbin-bagel-7b-v0.5 with Transformers:

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

pipe = pipeline("text-generation", model="hflog/jondurbin-bagel-7b-v0.5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("hflog/jondurbin-bagel-7b-v0.5")
model = AutoModelForMultimodalLM.from_pretrained("hflog/jondurbin-bagel-7b-v0.5")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hflog/jondurbin-bagel-7b-v0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hflog/jondurbin-bagel-7b-v0.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hflog/jondurbin-bagel-7b-v0.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hflog/jondurbin-bagel-7b-v0.5

SGLang

How to use hflog/jondurbin-bagel-7b-v0.5 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 "hflog/jondurbin-bagel-7b-v0.5" \
    --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": "hflog/jondurbin-bagel-7b-v0.5",
		"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 "hflog/jondurbin-bagel-7b-v0.5" \
        --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": "hflog/jondurbin-bagel-7b-v0.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hflog/jondurbin-bagel-7b-v0.5 with Docker Model Runner:
```
docker model run hf.co/hflog/jondurbin-bagel-7b-v0.5
```

jondurbin-bagel-7b-v0.5 / bagel.png

hflog

Duplicate from jondurbin/bagel-7b-v0.5

c83e8ed verified about 2 years ago

Download

History Blame Contribute Delete

2.25 MB

Xet Pointer Details

( Raw pointer file )

Xet hash:: 3a4e43894953d0503f8b179929a32f4bec3e6101c3af743f089105c2bf526057
Size of remote file:: 2.25 MB
SHA256:: cf584728d30148a9e0002f5465829521cf3f0338e5a9951d4465543ad76021c0

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