Instructions to use Noodlz/QueenLiz-120B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Noodlz/QueenLiz-120B with Transformers:

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

pipe = pipeline("text-generation", model="Noodlz/QueenLiz-120B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Noodlz/QueenLiz-120B")
model = AutoModelForCausalLM.from_pretrained("Noodlz/QueenLiz-120B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Noodlz/QueenLiz-120B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Noodlz/QueenLiz-120B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Noodlz/QueenLiz-120B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Noodlz/QueenLiz-120B

SGLang

How to use Noodlz/QueenLiz-120B 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 "Noodlz/QueenLiz-120B" \
    --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": "Noodlz/QueenLiz-120B",
		"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 "Noodlz/QueenLiz-120B" \
        --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": "Noodlz/QueenLiz-120B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Noodlz/QueenLiz-120B with Docker Model Runner:
```
docker model run hf.co/Noodlz/QueenLiz-120B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

My first ever successful merge: QueenLiz 120B

this is a linear merge of Quartet70B (https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001) and Lzlv 70B (https://huggingface.co/lizpreciatior/lzlv_70b_fp16_hf)

Sharing it here so hopefully someone else with proper machine can try this out.

NOTE: Context Window should be 32K

My Q4KM GGUF here :https://huggingface.co/Noodlz/QueenLiz-120B-GGUF

Thanks to the Mad Skills by @mradermacher - a whole set of iMat quantized GGUF files here: https://huggingface.co/mradermacher/QueenLiz-120B-i1-GGUF/tree/main

base_model:

alchemonaut/QuartetAnemoi-70B-t0.0001
lizpreciatior/lzlv_70b_fp16_hf library_name: transformers tags:
mergekit
merge

output_folder

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

license: other license_name: non-commercial-research-only license_link: LICENSE

Downloads last month: 3

Safetensors

Model size

120B params

Tensor type

F16

Model tree for Noodlz/QueenLiz-120B

Quantizations

2 models

Paper for Noodlz/QueenLiz-120B

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 9