Instructions to use JYL480/Test_DistBERTModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JYL480/Test_DistBERTModel with Transformers:

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

pipe = pipeline("text-generation", model="JYL480/Test_DistBERTModel")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JYL480/Test_DistBERTModel")
model = AutoModelForCausalLM.from_pretrained("JYL480/Test_DistBERTModel")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JYL480/Test_DistBERTModel with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JYL480/Test_DistBERTModel"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JYL480/Test_DistBERTModel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JYL480/Test_DistBERTModel

SGLang

How to use JYL480/Test_DistBERTModel 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 "JYL480/Test_DistBERTModel" \
    --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": "JYL480/Test_DistBERTModel",
		"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 "JYL480/Test_DistBERTModel" \
        --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": "JYL480/Test_DistBERTModel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JYL480/Test_DistBERTModel with Docker Model Runner:
```
docker model run hf.co/JYL480/Test_DistBERTModel
```

JYL480 commited on Jul 10, 2024

Commit

73753f5

verified ·

1 Parent(s): 29090b2

End of training

Browse files

Files changed (4) hide show

README.md +7 -5
model.safetensors +1 -1
runs/Jul10_07-26-37_fdac1b9d0fac/events.out.tfevents.1720596398.fdac1b9d0fac.1598.2 +2 -2
runs/Jul10_07-26-37_fdac1b9d0fac/events.out.tfevents.1720598045.fdac1b9d0fac.1598.3 +3 -0

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.7988
 ## Model description
@@ -42,15 +42,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.9539        | 1.0   | 1297 | 3.8117          |
-| 3.8697        | 2.0   | 2594 | 3.8012          |
-| 3.8171        | 3.0   | 3891 | 3.7988          |
 ### Framework versions

 This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset.
 It achieves the following results on the evaluation set:
+- Loss: 3.7960
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 3.9536        | 1.0   | 1297 | 3.8110          |
+| 3.8647        | 2.0   | 2594 | 3.7992          |
+| 3.8013        | 3.0   | 3891 | 3.7953          |
+| 3.7728        | 4.0   | 5188 | 3.7968          |
+| 3.7431        | 5.0   | 6485 | 3.7960          |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239c11e63d12e6cca49a0184ca1a9c82b2c4b9958094d8ef89f452c0dc6b0918
 size 327657928

 version https://git-lfs.github.com/spec/v1
+oid sha256:9a6bdd90c36c9135bb34c5a7c3684e63aa67c038d56a2949c84425bfcbf37c24
 size 327657928

runs/Jul10_07-26-37_fdac1b9d0fac/events.out.tfevents.1720596398.fdac1b9d0fac.1598.2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7fee2ecfff05f917ed24f3c521dafb500ae0f35a339b3973ae9c2b5547ea7a
-size 8775

 version https://git-lfs.github.com/spec/v1
+oid sha256:9ae183bec99be81e3b04ca85453467c46cbe68111f85057806e40b575f2f3c26
+size 9400

runs/Jul10_07-26-37_fdac1b9d0fac/events.out.tfevents.1720598045.fdac1b9d0fac.1598.3 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8221c9ffe1f288ad605a9f51d2791f72586082895909fb1322e53d9d57adf2
+size 359