Instructions to use ajtaltarabukin2022/merged_champion_v5_m4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajtaltarabukin2022/merged_champion_v5_m4 with Transformers:

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

pipe = pipeline("text-generation", model="ajtaltarabukin2022/merged_champion_v5_m4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ajtaltarabukin2022/merged_champion_v5_m4")
model = AutoModelForCausalLM.from_pretrained("ajtaltarabukin2022/merged_champion_v5_m4", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ajtaltarabukin2022/merged_champion_v5_m4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajtaltarabukin2022/merged_champion_v5_m4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajtaltarabukin2022/merged_champion_v5_m4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ajtaltarabukin2022/merged_champion_v5_m4

SGLang

How to use ajtaltarabukin2022/merged_champion_v5_m4 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 "ajtaltarabukin2022/merged_champion_v5_m4" \
    --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": "ajtaltarabukin2022/merged_champion_v5_m4",
		"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 "ajtaltarabukin2022/merged_champion_v5_m4" \
        --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": "ajtaltarabukin2022/merged_champion_v5_m4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ajtaltarabukin2022/merged_champion_v5_m4 with Docker Model Runner:
```
docker model run hf.co/ajtaltarabukin2022/merged_champion_v5_m4
```

merged_champion_v5_m4

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear merge method using dura-lori/affine-5ED5dwT4fztHjgjyR6vXpbGfnooeuWfr3VueaZrrfWJSou7y as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: dura-lori/affine-5ED5dwT4fztHjgjyR6vXpbGfnooeuWfr3VueaZrrfWJSou7y
dtype: bfloat16
merge_method: linear
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 64]
        model: dura-lori/affine-5ED5dwT4fztHjgjyR6vXpbGfnooeuWfr3VueaZrrfWJSou7y
        parameters:
          weight: 0.35
      - layer_range: [0, 64]
        model: voidai001/affine-rl0-5HeJuQB4ZcVaU8yfgwYCm3AvdiA7dPA34nvB5HwSubVoFREm
        parameters:
          weight: 0.3
      - layer_range: [0, 64]
        model: chouchouM/Affine-5DhGPvYiBChDerVjSgyt1vuuwQyZWJJgsEdQHAkXRuSYji4d
        parameters:
          weight: 0.2
      - layer_range: [0, 64]
        model: dura-lori/affine-5CtqFaxMkR1rZfP3cWiW6ywTszxd6dKqFoPtKdLQzMkT1kCf
        parameters:
          weight: 0.15
parameters:
  int8_mask: 0.0
  normalize: 1.0
tokenizer_source: base

Downloads last month: 11

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for ajtaltarabukin2022/merged_champion_v5_m4

Base model

chouchouM/Affine-5DhGPvYiBChDerVjSgyt1vuuwQyZWJJgsEdQHAkXRuSYji4d

Finetuned

(3)

this model

Paper for ajtaltarabukin2022/merged_champion_v5_m4

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 9