Instructions to use brucethemoose/SUS-Bagel-200K-DARE-Test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brucethemoose/SUS-Bagel-200K-DARE-Test with Transformers:

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

pipe = pipeline("text-generation", model="brucethemoose/SUS-Bagel-200K-DARE-Test")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brucethemoose/SUS-Bagel-200K-DARE-Test")
model = AutoModelForCausalLM.from_pretrained("brucethemoose/SUS-Bagel-200K-DARE-Test", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use brucethemoose/SUS-Bagel-200K-DARE-Test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brucethemoose/SUS-Bagel-200K-DARE-Test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brucethemoose/SUS-Bagel-200K-DARE-Test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brucethemoose/SUS-Bagel-200K-DARE-Test

SGLang

How to use brucethemoose/SUS-Bagel-200K-DARE-Test 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 "brucethemoose/SUS-Bagel-200K-DARE-Test" \
    --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": "brucethemoose/SUS-Bagel-200K-DARE-Test",
		"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 "brucethemoose/SUS-Bagel-200K-DARE-Test" \
        --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": "brucethemoose/SUS-Bagel-200K-DARE-Test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use brucethemoose/SUS-Bagel-200K-DARE-Test with Docker Model Runner:
```
docker model run hf.co/brucethemoose/SUS-Bagel-200K-DARE-Test
```

Just an experiment to try and extend the context of SUS, a 4K Yi model, and DPO Bagel, which breaks down after 4K context. Yi 4K was used as a base (even for bagel which is technically a Yi 200K model), and Yi 200K is merged in with a density of 1.

I wanted to include Hermes 34B, but something funky about its tokenizer breaks mergekit.

A component of another merge. Auto generated mergekit description below:

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 /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama as a base.

Models Merged

The following models were included in the merge:

/home/alpha/Models/Raw/SUSTech_SUS-Chat-34B
/home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
/home/alpha/Models/Raw/jondurbin_bagel-34b-v0.2
/home/alpha/Models/Raw/jondurbin_bagel-dpo-34b-v0.2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
  # No parameters necessary for base model
  - model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
    parameters:
      weight: 0.5
      density: 1
  - model: /home/alpha/Models/Raw/SUSTech_SUS-Chat-34B
    parameters:
      weight: 0.2
      density: 0.12
  - model: /home/alpha/Models/Raw/jondurbin_bagel-dpo-34b-v0.2
    parameters:
      weight: 0.2
      density: 0.15
  - model: /home/alpha/Models/Raw/jondurbin_bagel-34b-v0.2
    parameters:
      weight: 0.1
      density: 0.12
merge_method: dare_ties
tokenizer_source: union
base_model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
parameters:
  int8_mask: true
dtype: bfloat16

Downloads last month: 59

Safetensors

Model size

34B params

Tensor type

BF16

Space using brucethemoose/SUS-Bagel-200K-DARE-Test 1

Papers for brucethemoose/SUS-Bagel-200K-DARE-Test

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

Paper • 2311.03099 • Published Nov 6, 2023 • 38

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19