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

Libraries

How to use kaizerBox/gpt2-summarization with Transformers:

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

pipe = pipeline("text-generation", model="kaizerBox/gpt2-summarization")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaizerBox/gpt2-summarization")
model = AutoModelForCausalLM.from_pretrained("kaizerBox/gpt2-summarization")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kaizerBox/gpt2-summarization with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kaizerBox/gpt2-summarization

SGLang

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

Docker Model Runner
How to use kaizerBox/gpt2-summarization with Docker Model Runner:
```
docker model run hf.co/kaizerBox/gpt2-summarization
```

kaizerBox commited on Nov 28, 2023

Commit

ec348d3

1 Parent(s): ee639dc

Time is 194.93288735946018 minutes, Memory is 9.5GB

Browse files

Files changed (5) hide show

README.md +4 -4
config.json +4 -4
model.safetensors +2 -2
runs/Nov28_15-03-43_940adb247ee4/events.out.tfevents.1701183823.940adb247ee4.323.0 +3 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [](https://huggingface.co/) on the xsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.1524
 ## Model description
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 4.9693        | 1.0   | 5762  | 4.3526          |
-| 4.4387        | 2.0   | 11525 | 4.1929          |
-| 4.3335        | 3.0   | 17286 | 4.1524          |
 ### Framework versions

 This model is a fine-tuned version of [](https://huggingface.co/) on the xsum dataset.
 It achieves the following results on the evaluation set:
+- Loss: 4.0256
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
+| 4.7214        | 1.0   | 5762  | 4.2254          |
+| 4.1228        | 2.0   | 11525 | 4.0669          |
+| 4.0011        | 3.0   | 17286 | 4.0256          |
 ### Framework versions

config.json CHANGED Viewed

@@ -3,20 +3,20 @@
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_embd": 128,
   "n_head": 2,
-  "n_inner": 216,
   "n_layer": 3,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,

   "architectures": [
     "GPT2LMHeadModel"
   ],
+  "attn_pdrop": 0.0,
   "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_embd": 128,
   "n_head": 2,
+  "n_inner": 128,
   "n_layer": 3,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffc2e22af735d871cabae0e6f33c79c063b01fccff67046866a93141a9da6741
-size 27728168

 version https://git-lfs.github.com/spec/v1
+oid sha256:e54bcc781ea24987eb720ec863042cd076ba2bcb8b84faaea8a5d35d40deabf2
+size 27456776

runs/Nov28_15-03-43_940adb247ee4/events.out.tfevents.1701183823.940adb247ee4.323.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa8b58e2c3d5408de47f0c098f4f7055fc7e07ce33ec1db74babf41dd30ffbd
+size 5922

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf7defc4a7030a5b3580a4dc0a1031e5672ad75f73f1f43c06ed5d993f77c80
 size 4600

 version https://git-lfs.github.com/spec/v1
+oid sha256:b9596d478b85074461b1bd9e3792f4de79e2758b9a5be432bc062f673ddf0c22
 size 4600