Instructions to use xiaorui638/mistral_merged8_ties with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xiaorui638/mistral_merged8_ties with Transformers:

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

pipe = pipeline("text-generation", model="xiaorui638/mistral_merged8_ties")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xiaorui638/mistral_merged8_ties")
model = AutoModelForCausalLM.from_pretrained("xiaorui638/mistral_merged8_ties")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xiaorui638/mistral_merged8_ties with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xiaorui638/mistral_merged8_ties"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xiaorui638/mistral_merged8_ties",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xiaorui638/mistral_merged8_ties

SGLang

How to use xiaorui638/mistral_merged8_ties 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 "xiaorui638/mistral_merged8_ties" \
    --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": "xiaorui638/mistral_merged8_ties",
		"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 "xiaorui638/mistral_merged8_ties" \
        --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": "xiaorui638/mistral_merged8_ties",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xiaorui638/mistral_merged8_ties with Docker Model Runner:
```
docker model run hf.co/xiaorui638/mistral_merged8_ties
```

merged_models_8

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

Merge Details

Merge Method

This model was merged using the TIES merge method using mistralai/Mistral-7B-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:

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: OpenPipe/mistral-ft-optimized-1218
    parameters:
      density: 0.5
      weight: 0.4
  - model: mlabonne/NeuralHermes-2.5-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.3
  - model: HuggingFaceH4/zephyr-7b-beta
    parameters:
      density: 0.5
      weight: 0.3
  - model: nvidia/OpenMath-Mistral-7B-v0.1-hf
    parameters:
      density: 0.5
      weight: 0.2
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.5
  - model: teknium/CollectiveCognition-v1.1-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.3
  - model: NousResearch/Hermes-2-Pro-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.3
  - model: HuggingFaceH4/zephyr-7b-alpha
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
dtype: float16