Instructions to use eliwill/gpt2-finetuned-krishna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eliwill/gpt2-finetuned-krishna with Transformers:

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

pipe = pipeline("text-generation", model="eliwill/gpt2-finetuned-krishna")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eliwill/gpt2-finetuned-krishna")
model = AutoModelForCausalLM.from_pretrained("eliwill/gpt2-finetuned-krishna")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use eliwill/gpt2-finetuned-krishna with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/eliwill/gpt2-finetuned-krishna

SGLang

How to use eliwill/gpt2-finetuned-krishna 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 "eliwill/gpt2-finetuned-krishna" \
    --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": "eliwill/gpt2-finetuned-krishna",
		"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 "eliwill/gpt2-finetuned-krishna" \
        --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": "eliwill/gpt2-finetuned-krishna",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eliwill/gpt2-finetuned-krishna with Docker Model Runner:
```
docker model run hf.co/eliwill/gpt2-finetuned-krishna
```

eliwill commited on Apr 27, 2022

Commit

e045226

1 Parent(s): c7b8874

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -4

README.md CHANGED Viewed

@@ -1,7 +1,4 @@
 ---
-license: mit
-tags:
-- generated_from_keras_callback
 model-index:
 - name: eliwill/gpt2-finetuned-krishna
   results: []
@@ -12,7 +9,7 @@ probably proofread and complete it, then remove this comment. -->
 # eliwill/gpt2-finetuned-krishna
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Train Loss: 3.4997
 - Validation Loss: 3.6853

 ---
 model-index:
 - name: eliwill/gpt2-finetuned-krishna
   results: []
 # eliwill/gpt2-finetuned-krishna
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on a collection of books by Jiddu Krishnamurti.
 It achieves the following results on the evaluation set:
 - Train Loss: 3.4997
 - Validation Loss: 3.6853