Instructions to use Aryanne/sheared-plus-westlake-50_75p with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aryanne/sheared-plus-westlake-50_75p with Transformers:

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

pipe = pipeline("text-generation", model="Aryanne/sheared-plus-westlake-50_75p")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aryanne/sheared-plus-westlake-50_75p")
model = AutoModelForCausalLM.from_pretrained("Aryanne/sheared-plus-westlake-50_75p")

llama-cpp-python

How to use Aryanne/sheared-plus-westlake-50_75p with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Aryanne/sheared-plus-westlake-50_75p",
	filename="q4_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Aryanne/sheared-plus-westlake-50_75p with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0
# Run inference directly in the terminal:
llama-cli -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0
# Run inference directly in the terminal:
llama-cli -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Aryanne/sheared-plus-westlake-50_75p:Q4_0

Use Docker

docker model run hf.co/Aryanne/sheared-plus-westlake-50_75p:Q4_0

LM Studio
Jan

vLLM

How to use Aryanne/sheared-plus-westlake-50_75p with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aryanne/sheared-plus-westlake-50_75p"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aryanne/sheared-plus-westlake-50_75p",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Aryanne/sheared-plus-westlake-50_75p:Q4_0

SGLang

How to use Aryanne/sheared-plus-westlake-50_75p 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 "Aryanne/sheared-plus-westlake-50_75p" \
    --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": "Aryanne/sheared-plus-westlake-50_75p",
		"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 "Aryanne/sheared-plus-westlake-50_75p" \
        --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": "Aryanne/sheared-plus-westlake-50_75p",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Aryanne/sheared-plus-westlake-50_75p with Ollama:
```
ollama run hf.co/Aryanne/sheared-plus-westlake-50_75p:Q4_0
```

Unsloth Studio new

How to use Aryanne/sheared-plus-westlake-50_75p with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Aryanne/sheared-plus-westlake-50_75p to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Aryanne/sheared-plus-westlake-50_75p to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Aryanne/sheared-plus-westlake-50_75p to start chatting

Docker Model Runner
How to use Aryanne/sheared-plus-westlake-50_75p with Docker Model Runner:
```
docker model run hf.co/Aryanne/sheared-plus-westlake-50_75p:Q4_0
```

Lemonade

How to use Aryanne/sheared-plus-westlake-50_75p with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Aryanne/sheared-plus-westlake-50_75p:Q4_0

Run and chat with the model

lemonade run user.sheared-plus-westlake-50_75p-Q4_0

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Another trial of merging models with different sizes, still under testing, should be more stable, but I have no ideia if it's improving or degrading the base model.

In this I changed something, to have more Westlake. Recipe:

merge_method: task_anysize
base_model: princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
models:
  - model: senseable/WestLake-7B-v2
    parameters:
      weight: 1.0
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	36.31
AI2 Reasoning Challenge (25-Shot)	34.04
HellaSwag (10-Shot)	58.05
MMLU (5-Shot)	26.24
TruthfulQA (0-shot)	42.64
Winogrande (5-shot)	56.91
GSM8k (5-shot)	0.00

Downloads last month: 223

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Aryanne/sheared-plus-westlake-50_75p

Quantizations

2 models

Collection including Aryanne/sheared-plus-westlake-50_75p

Testing Might be broken

Collection

testing only models, • 8 items • Updated Mar 2 • 2

Evaluation results

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

34.040
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

58.050
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

26.240
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

42.640
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

56.910
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.000