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

Libraries

How to use mafgit/empathetic-distilgpt2 with Transformers:

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

pipe = pipeline("text-generation", model="mafgit/empathetic-distilgpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mafgit/empathetic-distilgpt2")
model = AutoModelForCausalLM.from_pretrained("mafgit/empathetic-distilgpt2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mafgit/empathetic-distilgpt2 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mafgit/empathetic-distilgpt2

SGLang

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

Docker Model Runner
How to use mafgit/empathetic-distilgpt2 with Docker Model Runner:
```
docker model run hf.co/mafgit/empathetic-distilgpt2
```

mafgit commited on May 1

Commit

fd03a26

verified ·

1 Parent(s): 172bace

End of training

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ 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 Estwld/empathetic_dialogues_llm dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7130
 ## Model description

 This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the Estwld/empathetic_dialogues_llm dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.8987
 ## Model description