Instructions to use mergekit-community/mergekit-model_stock-hwudfad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mergekit-community/mergekit-model_stock-hwudfad with Transformers:

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

pipe = pipeline("text-generation", model="mergekit-community/mergekit-model_stock-hwudfad")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mergekit-community/mergekit-model_stock-hwudfad")
model = AutoModelForMultimodalLM.from_pretrained("mergekit-community/mergekit-model_stock-hwudfad")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mergekit-community/mergekit-model_stock-hwudfad with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mergekit-community/mergekit-model_stock-hwudfad

SGLang

How to use mergekit-community/mergekit-model_stock-hwudfad 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 "mergekit-community/mergekit-model_stock-hwudfad" \
    --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": "mergekit-community/mergekit-model_stock-hwudfad",
		"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 "mergekit-community/mergekit-model_stock-hwudfad" \
        --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": "mergekit-community/mergekit-model_stock-hwudfad",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mergekit-community/mergekit-model_stock-hwudfad with Docker Model Runner:
```
docker model run hf.co/mergekit-community/mergekit-model_stock-hwudfad
```

mergekit-model_stock-hwudfad

File size: 2,288 Bytes

8e1549f

---
base_model:
- Envoid/MN-12B-Tarsus
- mergekit-community/mergekit-slerp-zbeneng
- Tokerss/NeoMixUnleashedFineTuned
- mergekit-community/mergekit-ties-crxzkjs
- Nohobby/MN-12B-Siskin-v0.2
- matchaaaaa/MN-Tiramisu-12B
- LatitudeGames/Wayfarer-12B
- mergekit-community/mergekit-slerp-yvvcncu
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mergekit-community/mergekit-slerp-yvvcncu](https://huggingface.co/mergekit-community/mergekit-slerp-yvvcncu) as a base.

### Models Merged

The following models were included in the merge:
* [Envoid/MN-12B-Tarsus](https://huggingface.co/Envoid/MN-12B-Tarsus)
* [mergekit-community/mergekit-slerp-zbeneng](https://huggingface.co/mergekit-community/mergekit-slerp-zbeneng)
* [Tokerss/NeoMixUnleashedFineTuned](https://huggingface.co/Tokerss/NeoMixUnleashedFineTuned)
* [mergekit-community/mergekit-ties-crxzkjs](https://huggingface.co/mergekit-community/mergekit-ties-crxzkjs)
* [Nohobby/MN-12B-Siskin-v0.2](https://huggingface.co/Nohobby/MN-12B-Siskin-v0.2)
* [matchaaaaa/MN-Tiramisu-12B](https://huggingface.co/matchaaaaa/MN-Tiramisu-12B)
* [LatitudeGames/Wayfarer-12B](https://huggingface.co/LatitudeGames/Wayfarer-12B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/mergekit-slerp-yvvcncu
models:
  - model: mergekit-community/mergekit-slerp-yvvcncu
    parameters:
      weight: 1
  - model: LatitudeGames/Wayfarer-12B
    parameters:
      weight: .9
  - model: Envoid/MN-12B-Tarsus
    parameters:
      weight: .9
  - model: mergekit-community/mergekit-slerp-zbeneng
    parameters:
      weight: .9
  - model: matchaaaaa/MN-Tiramisu-12B
    parameters:
      weight: .9
  - model: Nohobby/MN-12B-Siskin-v0.2
    parameters:
      weight: 0.8
  - model: Tokerss/NeoMixUnleashedFineTuned
    parameters:
      weight: 0.6
  - model: mergekit-community/mergekit-ties-crxzkjs
    parameters:
      weight: 0.5
parameters:
  normalize: true
```