Instructions to use dnagpt/gpt2-small-openweb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dnagpt/gpt2-small-openweb with Transformers:

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

pipe = pipeline("text-generation", model="dnagpt/gpt2-small-openweb")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dnagpt/gpt2-small-openweb")
model = AutoModelForCausalLM.from_pretrained("dnagpt/gpt2-small-openweb")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dnagpt/gpt2-small-openweb with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dnagpt/gpt2-small-openweb

SGLang

How to use dnagpt/gpt2-small-openweb 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 "dnagpt/gpt2-small-openweb" \
    --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": "dnagpt/gpt2-small-openweb",
		"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 "dnagpt/gpt2-small-openweb" \
        --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": "dnagpt/gpt2-small-openweb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dnagpt/gpt2-small-openweb with Docker Model Runner:
```
docker model run hf.co/dnagpt/gpt2-small-openweb
```

marisming commited on Jan 15, 2025

Commit

76a183b

verified ·

1 Parent(s): 8fce7ff

Upload tokenizer

Browse files

Files changed (1) hide show

tokenizer_config.json +7 -0

tokenizer_config.json CHANGED Viewed

@@ -27,8 +27,15 @@
   },
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }

   },
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "max_length": 256,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }