Instructions to use rhplus0831/maid-yuzu-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rhplus0831/maid-yuzu-v4 with Transformers:

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

pipe = pipeline("text-generation", model="rhplus0831/maid-yuzu-v4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rhplus0831/maid-yuzu-v4")
model = AutoModelForCausalLM.from_pretrained("rhplus0831/maid-yuzu-v4")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rhplus0831/maid-yuzu-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rhplus0831/maid-yuzu-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhplus0831/maid-yuzu-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rhplus0831/maid-yuzu-v4

SGLang

How to use rhplus0831/maid-yuzu-v4 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 "rhplus0831/maid-yuzu-v4" \
    --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": "rhplus0831/maid-yuzu-v4",
		"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 "rhplus0831/maid-yuzu-v4" \
        --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": "rhplus0831/maid-yuzu-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rhplus0831/maid-yuzu-v4 with Docker Model Runner:
```
docker model run hf.co/rhplus0831/maid-yuzu-v4
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

maid-yuzu-v4

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

This model is a model that I merged with several models I know because I had leftover credits for merging. Of course, the results are not good. Please do not use it.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mistralai/Mixtral-8x7B-v0.1 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:
  model:
    path: mistralai/Mixtral-8x7B-v0.1
dtype: bfloat16
merge_method: dare_ties
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: smelborp/MixtralOrochi8x7B
    parameters:
      density: 0.75
      weight: 0.7
  - layer_range: [0, 32]
    model:
      model:
        path: cognitivecomputations/dolphin-2.7-mixtral-8x7b
    parameters:
      density: 0.6
      weight: 0.1
  - layer_range: [0, 32]
    model:
      model:
        path: jondurbin/bagel-dpo-8x7b-v0.2
    parameters:
      density: 0.6
      weight: 0.1
  - layer_range: [0, 32]
    model:
      lora:
        path: Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora
      model:
        path: mistralai/Mixtral-8x7B-v0.1
    parameters:
      density: 0.5
      weight: 0.25
  - layer_range: [0, 32]
    model:
      model:
        path: Sao10K/Sensualize-Mixtral-bf16
    parameters:
      density: 0.5
      weight: 0.2
  - layer_range: [0, 32]
    model:
      model:
        path: mistralai/Mixtral-8x7B-v0.1