Instructions to use rony/gpt2-quantized-jokes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rony/gpt2-quantized-jokes with Transformers:

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

pipe = pipeline("text-generation", model="rony/gpt2-quantized-jokes")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rony/gpt2-quantized-jokes")
model = AutoModelForCausalLM.from_pretrained("rony/gpt2-quantized-jokes")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rony/gpt2-quantized-jokes with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rony/gpt2-quantized-jokes

SGLang

How to use rony/gpt2-quantized-jokes 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 "rony/gpt2-quantized-jokes" \
    --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": "rony/gpt2-quantized-jokes",
		"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 "rony/gpt2-quantized-jokes" \
        --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": "rony/gpt2-quantized-jokes",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rony/gpt2-quantized-jokes with Docker Model Runner:
```
docker model run hf.co/rony/gpt2-quantized-jokes
```

rony commited on Jan 28, 2024

Commit

4bbd92c

verified ·

1 Parent(s): 9b56c83

Upload tokenizer

Browse files

Files changed (4) hide show

special_tokens_map.json +3 -21
tokenizer.json +0 -0
tokenizer_config.json +0 -3
vocab.json +0 -0

special_tokens_map.json CHANGED Viewed

@@ -1,23 +1,5 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
 }

 {
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "50256": {
@@ -14,9 +13,7 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "errors": "replace",
   "model_max_length": 1024,
-  "pad_token": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "50256": {
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

vocab.json CHANGED Viewed

The diff for this file is too large to render. See raw diff