Instructions to use Aero/Tsubomi-Haruno with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aero/Tsubomi-Haruno with Transformers:

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

pipe = pipeline("text-generation", model="Aero/Tsubomi-Haruno")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aero/Tsubomi-Haruno")
model = AutoModelForCausalLM.from_pretrained("Aero/Tsubomi-Haruno")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aero/Tsubomi-Haruno with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aero/Tsubomi-Haruno"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aero/Tsubomi-Haruno",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aero/Tsubomi-Haruno

SGLang

How to use Aero/Tsubomi-Haruno 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 "Aero/Tsubomi-Haruno" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aero/Tsubomi-Haruno",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Aero/Tsubomi-Haruno" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aero/Tsubomi-Haruno",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aero/Tsubomi-Haruno with Docker Model Runner:
```
docker model run hf.co/Aero/Tsubomi-Haruno
```

Aero commited on Jun 14, 2021

Commit

4addf3e

1 Parent(s): 30b0b35

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -8,8 +8,8 @@ license: mit
 ```python
 from transformers import AutoTokenizer, AutoModelWithLMHead
-tokenizer = AutoTokenizer.from_pretrained("Aero/Tsubomi-Haruno")
-model = AutoModelWithLMHead.from_pretrained("Aero/Tsubomi-Haruno")
 # Let's chat for 4 lines
 for step in range(4):
     # encode the new user input, add the eos_token and return a tensor in Pytorch
@@ -30,4 +30,4 @@ for step in range(4):
     # pretty print last ouput tokens from bot
     print("Tsubomi: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
-```

 ```python
 from transformers import AutoTokenizer, AutoModelWithLMHead
+tokenizer = AutoTokenizer.from_pretrained("r3dhummingbird/DialoGPT-medium-joshua")
+model = AutoModelWithLMHead.from_pretrained("r3dhummingbird/DialoGPT-medium-joshua")
 # Let's chat for 4 lines
 for step in range(4):
     # encode the new user input, add the eos_token and return a tensor in Pytorch
     # pretty print last ouput tokens from bot
     print("Tsubomi: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
+```