Instructions to use yedi-hu/Model_Kinship_2-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yedi-hu/Model_Kinship_2-2 with Transformers:

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

pipe = pipeline("text-generation", model="yedi-hu/Model_Kinship_2-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yedi-hu/Model_Kinship_2-2")
model = AutoModelForCausalLM.from_pretrained("yedi-hu/Model_Kinship_2-2")
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

vLLM

How to use yedi-hu/Model_Kinship_2-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yedi-hu/Model_Kinship_2-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yedi-hu/Model_Kinship_2-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yedi-hu/Model_Kinship_2-2

SGLang

How to use yedi-hu/Model_Kinship_2-2 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 "yedi-hu/Model_Kinship_2-2" \
    --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": "yedi-hu/Model_Kinship_2-2",
		"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 "yedi-hu/Model_Kinship_2-2" \
        --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": "yedi-hu/Model_Kinship_2-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yedi-hu/Model_Kinship_2-2 with Docker Model Runner:
```
docker model run hf.co/yedi-hu/Model_Kinship_2-2
```

This model is a checkpoint produced during iterative model merging experiments.
It is not intended as a final release but rather as an intermediate artifact that captures
the progression of merging steps. Researchers and practitioners can use it to study
the effects of incremental merging strategies, compare intermediate states, or build
upon this checkpoint in further experiments.

For more details, please refer to the paper: arXiv:2410.12613.

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

BF16

Paper for yedi-hu/Model_Kinship_2-2

Exploring Model Kinship for Merging Large Language Models

Paper • 2410.12613 • Published Oct 16, 2024 • 21