Instructions to use ivangrapher/merged_champion_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ivangrapher/merged_champion_v2 with Transformers:

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

pipe = pipeline("text-generation", model="ivangrapher/merged_champion_v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ivangrapher/merged_champion_v2")
model = AutoModelForCausalLM.from_pretrained("ivangrapher/merged_champion_v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ivangrapher/merged_champion_v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ivangrapher/merged_champion_v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ivangrapher/merged_champion_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ivangrapher/merged_champion_v2

SGLang

How to use ivangrapher/merged_champion_v2 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 "ivangrapher/merged_champion_v2" \
    --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": "ivangrapher/merged_champion_v2",
		"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 "ivangrapher/merged_champion_v2" \
        --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": "ivangrapher/merged_champion_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ivangrapher/merged_champion_v2 with Docker Model Runner:
```
docker model run hf.co/ivangrapher/merged_champion_v2
```

merged_champion_v2 / README.md

ivangrapher

Upload folder using huggingface_hub

03051d8 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

2.28 kB

metadata

base_model:
  - catKnowCoffiee/Affine2-5EPhxsSDWnNzYjZdupuC5WLi2a5M8FYfnkvo5ukWM8Yge9zi
  - dura-lori/affine-5FcYc4MZ2z9yfFp6qPBQQjtS3cXkDV7x46ZUcoUP3pFRGoj4
  - dura-lori/affine-5ED5dwT4fztHjgjyR6vXpbGfnooeuWfr3VueaZrrfWJSou7y
  - leary-comos/affine-5CSqun1nmHbJQuvxyvJ534ZBpbFUUT1hoWXAuj18k7Qs7g2R
library_name: transformers
tags:
  - mergekit
  - merge

merged_champion_v2

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

Merge Details

Merge Method

This model was merged using the DARE TIES 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: dare_ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 64]
        model: dura-lori/affine-5ED5dwT4fztHjgjyR6vXpbGfnooeuWfr3VueaZrrfWJSou7y
        parameters:
          weight: 0.45
      - layer_range: [0, 64]
        model: catKnowCoffiee/Affine2-5EPhxsSDWnNzYjZdupuC5WLi2a5M8FYfnkvo5ukWM8Yge9zi
        parameters:
          weight: 0.3
      - layer_range: [0, 64]
        model: dura-lori/affine-5FcYc4MZ2z9yfFp6qPBQQjtS3cXkDV7x46ZUcoUP3pFRGoj4
        parameters:
          weight: 0.15
      - layer_range: [0, 64]
        model: leary-comos/affine-5CSqun1nmHbJQuvxyvJ534ZBpbFUUT1hoWXAuj18k7Qs7g2R
        parameters:
          weight: 0.1
parameters:
  density: 0.3
  normalize: 1.0