Instructions to use alistairmcleay/user-simulator-gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alistairmcleay/user-simulator-gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="alistairmcleay/user-simulator-gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alistairmcleay/user-simulator-gpt2")
model = AutoModelForCausalLM.from_pretrained("alistairmcleay/user-simulator-gpt2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alistairmcleay/user-simulator-gpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alistairmcleay/user-simulator-gpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alistairmcleay/user-simulator-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alistairmcleay/user-simulator-gpt2

SGLang

How to use alistairmcleay/user-simulator-gpt2 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 "alistairmcleay/user-simulator-gpt2" \
    --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": "alistairmcleay/user-simulator-gpt2",
		"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 "alistairmcleay/user-simulator-gpt2" \
        --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": "alistairmcleay/user-simulator-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alistairmcleay/user-simulator-gpt2 with Docker Model Runner:
```
docker model run hf.co/alistairmcleay/user-simulator-gpt2
```

alistairmcleay commited on Jun 26, 2022

Commit

4a32042

1 Parent(s): c1397d2

Upload special_tokens_map.json

Browse files

Files changed (1) hide show

special_tokens_map.json +1 -0

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"bos_token": "<BOS>", "eos_token": "<EOS>", "sep_token": "<SEP>", "pad_token": "<PAD>", "additional_special_tokens": ["<CTX/>", "<USR/>", "<SYS/>", "</CTX>", "</USR>", "</SYS>", "<USR_UTT/>", "<SYS_UTT/>", "</USR_UTT>", "</SYS_UTT>", "<USR_ACT/>", "<SYS_ACT/>", "</USR_ACT>", "</SYS_ACT>", "<ACT/>", "<SLOT/>", "<VALUE/>", "</ACT>", "</SLOT>", "</VALUE>", "<GOAL/>", "<SCENARIO/>", "<TASK/>", "<DESC/>", "<INFORM/>", "<REQUEST/>", "</GOAL>", "</SCENARIO>", "</TASK>", "</DESC>", "</INFORM>", "</REQUEST>", "_INFORM_", "_REQUEST_", "_CONFIRM_", "_OFFER_", "_NOTIFY_SUCCESS_", "_NOTIFY_FAILURE_", "_INFORM_COUNT_", "_OFFER_INTENT_", "_REQ_MORE_", "_GOODBYE_", "_INFORM_INTENT_", "_NEGATE_INTENT_", "_AFFIRM_INTENT_", "_AFFIRM_", "_NEGATE_", "_SELECT_", "_REQUEST_ALTS_", "_THANK_YOU_", "_OFFER_BOOK_", "_GREET_", "_WELCOME_", "<INTENT/>", "</INTENT>", "_True_", "_False_", "_Empty_", "<SNT/>", "<GC/>", "<RA/>", "</SNT>", "</GC>", "</RA>"], "unk_token": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}