Instructions to use sumith2425/ppo-qlora-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sumith2425/ppo-qlora-model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2-medium")
model = PeftModel.from_pretrained(base_model, "sumith2425/ppo-qlora-model")

Transformers

How to use sumith2425/ppo-qlora-model with Transformers:

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

pipe = pipeline("text-generation", model="sumith2425/ppo-qlora-model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sumith2425/ppo-qlora-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sumith2425/ppo-qlora-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sumith2425/ppo-qlora-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sumith2425/ppo-qlora-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sumith2425/ppo-qlora-model

SGLang

How to use sumith2425/ppo-qlora-model 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 "sumith2425/ppo-qlora-model" \
    --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": "sumith2425/ppo-qlora-model",
		"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 "sumith2425/ppo-qlora-model" \
        --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": "sumith2425/ppo-qlora-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sumith2425/ppo-qlora-model with Docker Model Runner:
```
docker model run hf.co/sumith2425/ppo-qlora-model
```

sumith2425 commited on Feb 28

Commit

2f8709d

verified ·

1 Parent(s): 48bcf26

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

adapter_model.safetensors +1 -1
pytorch_model.bin +1 -1

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f3b3b3c81bc68ed061f0d7d324bd3c5e4c026e3fa88fa1f6dca778731fc331
 size 25190568

 version https://git-lfs.github.com/spec/v1
+oid sha256:3fe6b8d9c819521af2d828b88fbb231e16c0ec5002c4aad240eec46756a63d6c
 size 25190568

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae9519e81136d62770e7216cbc33c203fd27a357604f87bd9fb13ddde4bfd852
 size 6037

 version https://git-lfs.github.com/spec/v1
+oid sha256:ebaaa2388ba0b02d43e3b7a9f7d4b596d337ce875ad38dec155ff81c9cdde1d0
 size 6037