Instructions to use Kaoeiri/Qwenwify-32B-v2.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kaoeiri/Qwenwify-32B-v2.6 with Transformers:

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

pipe = pipeline("text-generation", model="Kaoeiri/Qwenwify-32B-v2.6")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Kaoeiri/Qwenwify-32B-v2.6")
model = AutoModelForMultimodalLM.from_pretrained("Kaoeiri/Qwenwify-32B-v2.6")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kaoeiri/Qwenwify-32B-v2.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kaoeiri/Qwenwify-32B-v2.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kaoeiri/Qwenwify-32B-v2.6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kaoeiri/Qwenwify-32B-v2.6

SGLang

How to use Kaoeiri/Qwenwify-32B-v2.6 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 "Kaoeiri/Qwenwify-32B-v2.6" \
    --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": "Kaoeiri/Qwenwify-32B-v2.6",
		"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 "Kaoeiri/Qwenwify-32B-v2.6" \
        --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": "Kaoeiri/Qwenwify-32B-v2.6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kaoeiri/Qwenwify-32B-v2.6 with Docker Model Runner:
```
docker model run hf.co/Kaoeiri/Qwenwify-32B-v2.6
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

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 unsloth/qwen2.5-32b as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
    parameters:
      weight: 0.9
      density: 0.82
  - model: AiCloser/Qwen2.5-32B-AGI
    parameters:
      weight: 0.24
      density: 0.76
  - model: crestf411/Q2.5-32B-Slush
    parameters:
      weight: 0.21
      density: 0.73
  - model: AXCXEPT/EZO-Qwen2.5-32B-Instruct
    parameters:
      weight: 0.18
      density: 0.71
  - model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
    parameters:
      weight: 0.19
      density: 0.72
  - model: huihui-ai/QwQ-32B-Preview-abliterated
    parameters:
      weight: 0.12
      density: 0.65
  - model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
    parameters:
      weight: 0.14
      density: 0.64
  - model: rombodawg/Rombos-LLM-V2.5-Qwen-32b
    parameters:
      weight: 0.11
      density: 0.65

merge_method: dare_ties
base_model: unsloth/qwen2.5-32b
parameters:
  density: 0.83
  epsilon: 0.06
  lambda: 1.22
dtype: bfloat16
tokenizer_source: union