Instructions to use yunconglong/DARE_TIES_13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yunconglong/DARE_TIES_13B with Transformers:

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

pipe = pipeline("text-generation", model="yunconglong/DARE_TIES_13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yunconglong/DARE_TIES_13B")
model = AutoModelForCausalLM.from_pretrained("yunconglong/DARE_TIES_13B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yunconglong/DARE_TIES_13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yunconglong/DARE_TIES_13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yunconglong/DARE_TIES_13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yunconglong/DARE_TIES_13B

SGLang

How to use yunconglong/DARE_TIES_13B 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 "yunconglong/DARE_TIES_13B" \
    --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": "yunconglong/DARE_TIES_13B",
		"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 "yunconglong/DARE_TIES_13B" \
        --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": "yunconglong/DARE_TIES_13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yunconglong/DARE_TIES_13B with Docker Model Runner:
```
docker model run hf.co/yunconglong/DARE_TIES_13B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DARE_TIES_13B

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 yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B as a base.

Models Merged

The following models were included in the merge:

./13B_DPO
./13B_MATH_DPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
    parameters:
      density: 1.0
      weight: 1.0
  - model: ./13B_MATH_DPO
    parameters:
      density: 0.5
      weight: [0.33, 0.4, 0.33]
  - model: ./13B_DPO
    parameters:
      density: [0.33, 0.45, 0.66]
      weight: 0.66
merge_method: dare_ties
base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16
tokenizer_source : union

Downloads last month: 7,967

Safetensors

Model size

13B params

Tensor type

BF16

Model tree for yunconglong/DARE_TIES_13B

Quantizations

1 model

Space using yunconglong/DARE_TIES_13B 1

Papers for yunconglong/DARE_TIES_13B

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 35

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19