Instructions to use cs552-the-expendables/kto_base_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs552-the-expendables/kto_base_base with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B")
model = PeftModel.from_pretrained(base_model, "cs552-the-expendables/kto_base_base")

Transformers

How to use cs552-the-expendables/kto_base_base with Transformers:

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

pipe = pipeline("text-generation", model="cs552-the-expendables/kto_base_base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("cs552-the-expendables/kto_base_base", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cs552-the-expendables/kto_base_base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs552-the-expendables/kto_base_base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs552-the-expendables/kto_base_base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs552-the-expendables/kto_base_base

SGLang

How to use cs552-the-expendables/kto_base_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 "cs552-the-expendables/kto_base_base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs552-the-expendables/kto_base_base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "cs552-the-expendables/kto_base_base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs552-the-expendables/kto_base_base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs552-the-expendables/kto_base_base with Docker Model Runner:
```
docker model run hf.co/cs552-the-expendables/kto_base_base
```

dimgor commited on 30 days ago

Commit

ef13fe6

verified ·

1 Parent(s): b75820b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -9,6 +9,8 @@ tags:
 - transformers
 - trl
 ---
 # Model Card for Model ID

 - transformers
 - trl
 ---
+> ⚠️ **Research artifact, not for clinical use.** Intermediate checkpoint from the PatientAgent project (patient simulator for benchmarking AI doctors). English-only; can hallucinate; **not** a medical device or evidence of clinical safety. See the project report for intended-use and ethics details.
 # Model Card for Model ID