Instructions to use ortofasfat/hh-open_assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ortofasfat/hh-open_assistant with Transformers:

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

pipe = pipeline("text-generation", model="ortofasfat/hh-open_assistant")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ortofasfat/hh-open_assistant")
model = AutoModelForCausalLM.from_pretrained("ortofasfat/hh-open_assistant", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ortofasfat/hh-open_assistant with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ortofasfat/hh-open_assistant

SGLang

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

Docker Model Runner
How to use ortofasfat/hh-open_assistant with Docker Model Runner:
```
docker model run hf.co/ortofasfat/hh-open_assistant
```

hh-open_assistant / generation_config.json

ortofasfat

Upload folder using huggingface_hub

01f7f37 over 3 years ago

Raw History Blame Contribute Delete

754 Bytes

{
  "_from_model_config": true,
  "bad_words_ids": [
    [
      434,
      15694,
      66,
      27,
      209
    ],
    [
      15362
    ],
    [
      1713
    ],
    [
      1713,
      64
    ],
    [
      1713,
      876
    ],
    [
      2016,
      251,
      857,
      75,
      9194,
      35478
    ],
    [
      2391
    ],
    [
      20340
    ],
    [
      33021
    ],
    [
      2391,
      1051
    ],
    [
      5638
    ],
    [
      2391,
      20340
    ],
    [
      5638,
      537
    ],
    [
      1559,
      2345
    ],
    [
      1559,
      7849
    ],
    [
      1559,
      17379
    ],
    [
      25321,
      4611
    ]
  ],
  "bos_token_id": 0,
  "eos_token_id": 0,
  "transformers_version": "4.28.1"
}

	{
	"_from_model_config": true,
	"bad_words_ids": [
	[
	434,
	15694,
	66,
	27,
	209
	],
	[
	15362
	],
	[
	1713
	],
	[
	1713,
	64
	],
	[
	1713,
	876
	],
	[
	2016,
	251,
	857,
	75,
	9194,
	35478
	],
	[
	2391
	],
	[
	20340
	],
	[
	33021
	],
	[
	2391,
	1051
	],
	[
	5638
	],
	[
	2391,
	20340
	],
	[
	5638,
	537
	],
	[
	1559,
	2345
	],
	[
	1559,
	7849
	],
	[
	1559,
	17379
	],
	[
	25321,
	4611
	]
	],
	"bos_token_id": 0,
	"eos_token_id": 0,
	"transformers_version": "4.28.1"
	}