Instructions to use bencyc1129/mitre-gpt2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bencyc1129/mitre-gpt2-base with Transformers:

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

pipe = pipeline("text-generation", model="bencyc1129/mitre-gpt2-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bencyc1129/mitre-gpt2-base")
model = AutoModelForCausalLM.from_pretrained("bencyc1129/mitre-gpt2-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bencyc1129/mitre-gpt2-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bencyc1129/mitre-gpt2-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bencyc1129/mitre-gpt2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bencyc1129/mitre-gpt2-base

SGLang

How to use bencyc1129/mitre-gpt2-base 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 "bencyc1129/mitre-gpt2-base" \
    --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": "bencyc1129/mitre-gpt2-base",
		"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 "bencyc1129/mitre-gpt2-base" \
        --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": "bencyc1129/mitre-gpt2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bencyc1129/mitre-gpt2-base with Docker Model Runner:
```
docker model run hf.co/bencyc1129/mitre-gpt2-base
```

bencyc1129 commited on Apr 9, 2024

Commit

bbb821d

verified ·

1 Parent(s): 7ca02ad

Training in progress, step 1000

Browse files

Files changed (3) hide show

model.safetensors +1 -1
runs/Apr09_22-55-31_f5af74300b2b/events.out.tfevents.1712703332.f5af74300b2b.5955.0 +3 -0
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74774a9d777039d076f8dcc31bfe1a963f77b40f30913805676dfcb6e8918ada
 size 500271744

 version https://git-lfs.github.com/spec/v1
+oid sha256:31ec06043cdf99a1abbc86d4c403f9b14042f4b163a1b36e94f22850a21416fb
 size 500271744

runs/Apr09_22-55-31_f5af74300b2b/events.out.tfevents.1712703332.f5af74300b2b.5955.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a954e4a56a4fe176cf3c4170dbc67b24699c36245b21b9987720769484b56549
+size 5284

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a70f2b6a179e533c99fa793a364d9663c6b941026f46b70622c86b9239a7a96
 size 4920

 version https://git-lfs.github.com/spec/v1
+oid sha256:7fa44e4058b0a9c790b52cb2586c51259fd89035ac296570c7ed7a1ddd81b3d9
 size 4920