Instructions to use ablam/distilgpt2_fine_tuned_gcode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ablam/distilgpt2_fine_tuned_gcode with Transformers:

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

pipe = pipeline("text-generation", model="ablam/distilgpt2_fine_tuned_gcode")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ablam/distilgpt2_fine_tuned_gcode")
model = AutoModelForCausalLM.from_pretrained("ablam/distilgpt2_fine_tuned_gcode")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ablam/distilgpt2_fine_tuned_gcode with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ablam/distilgpt2_fine_tuned_gcode"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ablam/distilgpt2_fine_tuned_gcode",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ablam/distilgpt2_fine_tuned_gcode

SGLang

How to use ablam/distilgpt2_fine_tuned_gcode 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 "ablam/distilgpt2_fine_tuned_gcode" \
    --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": "ablam/distilgpt2_fine_tuned_gcode",
		"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 "ablam/distilgpt2_fine_tuned_gcode" \
        --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": "ablam/distilgpt2_fine_tuned_gcode",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ablam/distilgpt2_fine_tuned_gcode with Docker Model Runner:
```
docker model run hf.co/ablam/distilgpt2_fine_tuned_gcode
```

ablam commited on Jun 10, 2022

Commit

e8ffb60

1 Parent(s): 2f476c2

Training in progress, step 500

Browse files

Files changed (4) hide show

pytorch_model.bin +1 -1
runs/Jun10_18-26-32_hal10/1654904530.7637877/events.out.tfevents.1654904530.hal10.596337.1 +3 -0
runs/Jun10_18-26-32_hal10/events.out.tfevents.1654904530.hal10.596337.0 +3 -0
training_args.bin +1 -1

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db38e510fe8734361bef936676182675c34308f206fd587d4e6b7e1ba0d6fa5
 size 333982173

 version https://git-lfs.github.com/spec/v1
+oid sha256:af5385386b097f7651293e16c75fe5c4179fd4da22eacb8c769fc475341b4591
 size 333982173

runs/Jun10_18-26-32_hal10/1654904530.7637877/events.out.tfevents.1654904530.hal10.596337.1 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d009936d6f466d546b5495b63f19ad1c83e81d9d2d9aa9ca4b382c9a83b34eb7
+size 4761

runs/Jun10_18-26-32_hal10/events.out.tfevents.1654904530.hal10.596337.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f36142ac39ed2dca90c410f032225dbd84fbd31b2894e768856b66a0bc5e508
+size 3837

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3141863ff65d675f6e0232273df116411d0be95d45b4453b6a71ea8932bc7298
 size 2991

 version https://git-lfs.github.com/spec/v1
+oid sha256:401ce72beab3ca8f773d39debdeb9181fdd90cd92ccb0b066ac3d0cfd10c6bb4
 size 2991