Instructions to use enryu43/anifusion_augmenter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use enryu43/anifusion_augmenter with Transformers:

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

pipe = pipeline("text-generation", model="enryu43/anifusion_augmenter")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("enryu43/anifusion_augmenter")
model = AutoModelForCausalLM.from_pretrained("enryu43/anifusion_augmenter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use enryu43/anifusion_augmenter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "enryu43/anifusion_augmenter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "enryu43/anifusion_augmenter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/enryu43/anifusion_augmenter

SGLang

How to use enryu43/anifusion_augmenter 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 "enryu43/anifusion_augmenter" \
    --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": "enryu43/anifusion_augmenter",
		"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 "enryu43/anifusion_augmenter" \
        --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": "enryu43/anifusion_augmenter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use enryu43/anifusion_augmenter with Docker Model Runner:
```
docker model run hf.co/enryu43/anifusion_augmenter
```

enryu43 commited on Oct 11, 2022

Commit

50012f0

1 Parent(s): fabc4d4

Add TF-converted checkpoint

Browse files

Files changed (2) hide show

config.json +1 -0
tf_model.h5 +3 -0

config.json CHANGED Viewed

@@ -15,6 +15,7 @@
   "n_inner": 1536,
   "n_layer": 6,
   "n_positions": 52,
   "pad_token_id": 2521,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

   "n_inner": 1536,
   "n_layer": 6,
   "n_positions": 52,
+  "name_or_path": "anifusion-prompt-augmenter",
   "pad_token_id": 2521,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

tf_model.h5 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9c36fd7918e7a9c97b090a7a57eb5835a448c0ba35d497d31c6be0415b221353
+size 121457624