Instructions to use bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2

SGLang

How to use bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 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 "bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2" \
    --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": "bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2",
		"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 "bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2" \
        --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": "bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 with Docker Model Runner:
```
docker model run hf.co/bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2
```

Exllama v2 Quantizations of Starling_Monarch_Westlake_Garten-7B-v0.1

Using turboderp's ExLlamaV2 v0.0.16 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1

Branch	Bits	lm_head bits	VRAM (4k)	VRAM (16k)	VRAM (32k)	Description
8_0	8.0	8.0	8.4 GB	9.8 GB	11.8 GB	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	8.0	7.2 GB	8.6 GB	10.6 GB	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	6.0	6.0 GB	7.4 GB	9.4 GB	Slightly lower quality vs 6.5, but usable on 8GB cards.
4_25	4.25	6.0	5.3 GB	6.7 GB	8.7 GB	GPTQ equivalent bits per weight, slightly higher quality.
3_5	3.5	6.0	4.7 GB	6.1 GB	8.1 GB	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 Starling_Monarch_Westlake_Garten-7B-v0.1-exl2-6_5

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download the main (only useful if you only care about measurement.json) branch to a folder called Starling_Monarch_Westlake_Garten-7B-v0.1-exl2:

mkdir Starling_Monarch_Westlake_Garten-7B-v0.1-exl2
huggingface-cli download bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 --local-dir Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

Linux:

mkdir Starling_Monarch_Westlake_Garten-7B-v0.1-exl2-6_5
huggingface-cli download bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 --revision 6_5 --local-dir Starling_Monarch_Westlake_Garten-7B-v0.1-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

mkdir Starling_Monarch_Westlake_Garten-7B-v0.1-exl2-6.5
huggingface-cli download bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2 --revision 6_5 --local-dir Starling_Monarch_Westlake_Garten-7B-v0.1-exl2-6.5 --local-dir-use-symlinks False

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-exl2

QuixiAI/WestLake-7B-v2-laser

berkeley-nest/Starling-LM-7B-alpha

mistralai/Mistral-7B-v0.1

mlabonne/AlphaMonarch-7B

senseable/garten2-7b

Merge model

this model

Evaluation results

self-reported on EQ-Bench
EQ-Bench v2.1

80.010
normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

71.760
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.150
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

65.070
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

67.920
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.160
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

71.950