Instructions to use hf-internal-testing/tiny-random-PegasusForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-PegasusForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/tiny-random-PegasusForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-PegasusForCausalLM")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/tiny-random-PegasusForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-PegasusForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-PegasusForCausalLM

SGLang

How to use hf-internal-testing/tiny-random-PegasusForCausalLM 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 "hf-internal-testing/tiny-random-PegasusForCausalLM" \
    --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": "hf-internal-testing/tiny-random-PegasusForCausalLM",
		"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 "hf-internal-testing/tiny-random-PegasusForCausalLM" \
        --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": "hf-internal-testing/tiny-random-PegasusForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-PegasusForCausalLM with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-PegasusForCausalLM
```

sgugger commited on Mar 28, 2023

Commit

a69f6d7

1 Parent(s): bedf3a4

Upload tiny models for PegasusForCausalLM

Browse files

Files changed (6) hide show

config.json +2 -3
generation_config.json +9 -0
pytorch_model.bin +2 -2
spiece.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +0 -1

config.json CHANGED Viewed

@@ -6,7 +6,6 @@
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classifier_dropout": 0.0,
   "d_model": 16,
   "decoder_attention_heads": 4,
   "decoder_ffn_dim": 4,
@@ -29,7 +28,7 @@
   "pad_token_id": 0,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.25.0.dev0",
   "use_cache": true,
-  "vocab_size": 1305
 }

   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
   "d_model": 16,
   "decoder_attention_heads": 4,
   "decoder_ffn_dim": 4,
   "pad_token_id": 0,
   "scale_embedding": false,
   "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
   "use_cache": true,
+  "vocab_size": 96103
 }

generation_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bafe071e293138636ffafdbfb862ebb82fc342785cb60e0c966f844d4695c54
-size 133657

 version https://git-lfs.github.com/spec/v1
+oid sha256:c72d59aa7198d32ea1ef56b5fc209db2d2fc950aa234398f50208dc26123fd7f
+size 6200729

spiece.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
+size 1912529

tokenizer.json CHANGED Viewed

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

tokenizer_config.json CHANGED Viewed

@@ -108,7 +108,6 @@
   "mask_token": "<mask_2>",
   "mask_token_sent": "<mask_1>",
   "model_max_length": 200,
-  "name_or_path": "google/pegasus-large",
   "offset": 103,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},

   "mask_token": "<mask_2>",
   "mask_token_sent": "<mask_1>",
   "model_max_length": 200,
   "offset": 103,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},