Instructions to use ntegrals/NeuralMerge-9B-Dare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ntegrals/NeuralMerge-9B-Dare with Transformers:

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

pipe = pipeline("text-generation", model="ntegrals/NeuralMerge-9B-Dare")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ntegrals/NeuralMerge-9B-Dare")
model = AutoModelForCausalLM.from_pretrained("ntegrals/NeuralMerge-9B-Dare")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ntegrals/NeuralMerge-9B-Dare with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ntegrals/NeuralMerge-9B-Dare"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ntegrals/NeuralMerge-9B-Dare",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ntegrals/NeuralMerge-9B-Dare

SGLang

How to use ntegrals/NeuralMerge-9B-Dare 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 "ntegrals/NeuralMerge-9B-Dare" \
    --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": "ntegrals/NeuralMerge-9B-Dare",
		"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 "ntegrals/NeuralMerge-9B-Dare" \
        --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": "ntegrals/NeuralMerge-9B-Dare",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ntegrals/NeuralMerge-9B-Dare with Docker Model Runner:
```
docker model run hf.co/ntegrals/NeuralMerge-9B-Dare
```

NeuralMerge-9B-Dare / README.md

ntegrals

Upload folder using huggingface_hub

8d3fce9 verified 11 months ago

preview code

Raw

History Blame Contribute Delete

1.6 kB

	---
	base_model:
	- samir-fama/SamirGPT-v1
	- EmbeddedLLM/Mistral-7B-Merge-14-v0.2
	- abacusai/Slerp-CM-mist-dpo
	- mistralai/Mistral-7B-v0.1
	library_name: transformers
	tags:
	- mergekit
	- merge

	---
	# merged

	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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.

	### Models Merged

	The following models were included in the merge:
	* [samir-fama/SamirGPT-v1](https://huggingface.co/samir-fama/SamirGPT-v1)
	* [EmbeddedLLM/Mistral-7B-Merge-14-v0.2](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.2)
	* [abacusai/Slerp-CM-mist-dpo](https://huggingface.co/abacusai/Slerp-CM-mist-dpo)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	base_model: mistralai/Mistral-7B-v0.1
	dtype: bfloat16
	merge_method: dare_ties
	modules:
	default:
	slices:
	- sources:
	- layer_range: [0, 32]
	model: mistralai/Mistral-7B-v0.1
	- layer_range: [0, 32]
	model: samir-fama/SamirGPT-v1
	parameters:
	density: 0.53
	weight: 0.4
	- layer_range: [0, 32]
	model: abacusai/Slerp-CM-mist-dpo
	parameters:
	density: 0.53
	weight: 0.3
	- layer_range: [0, 32]
	model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
	parameters:
	density: 0.53
	weight: 0.3
	parameters:
	int8_mask: 1.0
	```