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

Libraries

How to use auhide/gpt2-small-bgwiki with Transformers:

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

pipe = pipeline("text-generation", model="auhide/gpt2-small-bgwiki")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("auhide/gpt2-small-bgwiki")
model = AutoModelForCausalLM.from_pretrained("auhide/gpt2-small-bgwiki", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use auhide/gpt2-small-bgwiki with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/auhide/gpt2-small-bgwiki

SGLang

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

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

auhide commited on Apr 20, 2023

Commit

aa34518

1 Parent(s): a7132ab

Upload tokenizer

Browse files

Files changed (3) hide show

added_tokens.json +1 -0
special_tokens_map.json +1 -1
tokenizer.json +9 -0

added_tokens.json CHANGED Viewed

@@ -1,6 +1,7 @@
 {
   "[CLS]": 50257,
   "[EOL]": 50260,
   "[PAD]": 50259,
   "[SEP]": 50258
 }

 {
   "[CLS]": 50257,
   "[EOL]": 50260,
+  "[EOS]": 50261,
   "[PAD]": 50259,
   "[SEP]": 50258
 }

special_tokens_map.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "additional_special_tokens": [
-    "[EOL]"
   ],
   "bos_token": "[CLS]",
   "eos_token": "[SEP]",

 {
   "additional_special_tokens": [
+    "[EOS]"
   ],
   "bos_token": "[CLS]",
   "eos_token": "[SEP]",

tokenizer.json CHANGED Viewed

@@ -52,6 +52,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
     }
   ],
   "normalizer": null,

       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 50261,
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,