Instructions to use minnesotanlp/Finch-8B-KTO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minnesotanlp/Finch-8B-KTO with Transformers:

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

pipe = pipeline("text-generation", model="minnesotanlp/Finch-8B-KTO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("minnesotanlp/Finch-8B-KTO")
model = AutoModelForCausalLM.from_pretrained("minnesotanlp/Finch-8B-KTO", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use minnesotanlp/Finch-8B-KTO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "minnesotanlp/Finch-8B-KTO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "minnesotanlp/Finch-8B-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/minnesotanlp/Finch-8B-KTO

SGLang

How to use minnesotanlp/Finch-8B-KTO 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 "minnesotanlp/Finch-8B-KTO" \
    --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": "minnesotanlp/Finch-8B-KTO",
		"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 "minnesotanlp/Finch-8B-KTO" \
        --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": "minnesotanlp/Finch-8B-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use minnesotanlp/Finch-8B-KTO with Docker Model Runner:
```
docker model run hf.co/minnesotanlp/Finch-8B-KTO
```

passing2961 commited on Jun 30

Commit

8f32193

verified ·

1 Parent(s): 2627cfc

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -71,7 +71,7 @@ Evolution Fine-Tuning (EFT) turns evolutionary search **trajectories** into supe
 ## How to Use Finch
-1. **Execute OpenEvolve scaffold with Finch**
 Finch is a **mutation operator for evolutionary search**, most effective driven by a scaffold such as **OpenEvolve** (`T = 100`, temperature `0.7`, top-`p` `0.95`, up to `30K` tokens).
 You can also use other scaffolds in the [SkyDiscover](https://github.com/skydiscover-ai/skydiscover) framework, but we do not guarantee performance, as our model is trained on OpenEvolve's trajectories — one of this work's limitations.

 ## How to Use Finch
+1. **Execute OpenEvolve scaffold with Finch (vLLM serving, recommended)**
 Finch is a **mutation operator for evolutionary search**, most effective driven by a scaffold such as **OpenEvolve** (`T = 100`, temperature `0.7`, top-`p` `0.95`, up to `30K` tokens).
 You can also use other scaffolds in the [SkyDiscover](https://github.com/skydiscover-ai/skydiscover) framework, but we do not guarantee performance, as our model is trained on OpenEvolve's trajectories — one of this work's limitations.