Instructions to use Rocketknight1/distilgpt2-finetuned-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rocketknight1/distilgpt2-finetuned-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="Rocketknight1/distilgpt2-finetuned-wikitext2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rocketknight1/distilgpt2-finetuned-wikitext2")
model = AutoModelForCausalLM.from_pretrained("Rocketknight1/distilgpt2-finetuned-wikitext2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rocketknight1/distilgpt2-finetuned-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rocketknight1/distilgpt2-finetuned-wikitext2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rocketknight1/distilgpt2-finetuned-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rocketknight1/distilgpt2-finetuned-wikitext2

SGLang

How to use Rocketknight1/distilgpt2-finetuned-wikitext2 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 "Rocketknight1/distilgpt2-finetuned-wikitext2" \
    --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": "Rocketknight1/distilgpt2-finetuned-wikitext2",
		"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 "Rocketknight1/distilgpt2-finetuned-wikitext2" \
        --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": "Rocketknight1/distilgpt2-finetuned-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rocketknight1/distilgpt2-finetuned-wikitext2 with Docker Model Runner:
```
docker model run hf.co/Rocketknight1/distilgpt2-finetuned-wikitext2
```

Rocketknight1 HF Staff commited on Jan 28, 2022

Commit

d65da79

1 Parent(s): dfeb5f2

Training in progress epoch 0

Browse files

Files changed (4) hide show

README.md +3 -3
logs/train/events.out.tfevents.1643376063.matt-TRX40-AORUS-PRO-WIFI.13769.0.v2 +3 -0
logs/validation/events.out.tfevents.1643376187.matt-TRX40-AORUS-PRO-WIFI.13769.1.v2 +3 -0
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.8584
-- Validation Loss: 3.6755
 - Epoch: 0
 ## Model description
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.8584     | 3.6755          | 0     |
 ### Framework versions

 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 3.8577
+- Validation Loss: 3.6752
 - Epoch: 0
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
+| 3.8577     | 3.6752          | 0     |
 ### Framework versions

logs/train/events.out.tfevents.1643376063.matt-TRX40-AORUS-PRO-WIFI.13769.0.v2 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:66f766875185e75ce470ee93a142338c86e4f5894370aeb02f4c166d623d83e4
+size 1201176

logs/validation/events.out.tfevents.1643376187.matt-TRX40-AORUS-PRO-WIFI.13769.1.v2 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:03ec5cbe80f7231bb621c27a440b20cf2267ec798d17002954977cba0d32c9e2
+size 194

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1cd1d5ef4751094fe3b3efbf7f889969b33e1f61683ccd02d9fe99f8f92fe97
 size 327745496

 version https://git-lfs.github.com/spec/v1
+oid sha256:06fb2edd6d26a67275923f4ae3627356be6d186b21f36d7818fa6784a36362b1
 size 327745496