Instructions to use CalderaAI/30B-Lazarus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CalderaAI/30B-Lazarus with Transformers:

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

pipe = pipeline("text-generation", model="CalderaAI/30B-Lazarus")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CalderaAI/30B-Lazarus")
model = AutoModelForCausalLM.from_pretrained("CalderaAI/30B-Lazarus")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CalderaAI/30B-Lazarus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CalderaAI/30B-Lazarus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CalderaAI/30B-Lazarus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CalderaAI/30B-Lazarus

SGLang

How to use CalderaAI/30B-Lazarus 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 "CalderaAI/30B-Lazarus" \
    --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": "CalderaAI/30B-Lazarus",
		"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 "CalderaAI/30B-Lazarus" \
        --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": "CalderaAI/30B-Lazarus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CalderaAI/30B-Lazarus with Docker Model Runner:
```
docker model run hf.co/CalderaAI/30B-Lazarus
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

30B-Lazarus

Composition:

[] = applied as LoRA to a composite model | () = combined as composite models

[SuperCOT([gtp4xalpaca(manticorechatpygalpha+vicunaunlocked)]+[StoryV2(kaiokendev-SuperHOT-LoRA-prototype30b-8192)])]

This model is the result of an experimental use of LoRAs on language models and model merges that are not the base HuggingFace-format LLaMA model they were intended for. The desired outcome is to additively apply desired features without paradoxically watering down a model's effective behavior.

Potential limitations - LoRAs applied on top of each other may intercompete.

Subjective results - very promising. Further experimental tests and objective tests are required.

Instruct and Setup Suggestions:

Alpaca instruct is primary, Vicuna instruct format may work. If using KoboldAI or Text-Generation-WebUI, recommend switching between Godlike and Storywriter presets and adjusting output length + instructions in memory. Other presets as well as custom settings can yield highly different results, especially Temperature. If poking it with a stick doesn't work try poking harder.

Language Models and LoRAs Used Credits:

manticore-30b-chat-pyg-alpha [Epoch0.4] by openaccess-ai-collective

https://huggingface.co/openaccess-ai-collective/manticore-30b-chat-pyg-alpha

SuperCOT-LoRA [30B] by kaiokendev

https://huggingface.co/kaiokendev/SuperCOT-LoRA

Storytelling-LLaMa-LoRA [30B, Version 2] by GamerUnTouch

https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs

SuperHOT Prototype [30b 8k ctx] by kaiokendev

https://huggingface.co/kaiokendev/SuperHOT-LoRA-prototype

ChanSung's GPT4-Alpaca-LoRA https://huggingface.co/chansung/gpt4-alpaca-lora-30b

Neko-Institute-of-Science's Vicuna Unlocked LoRA (Checkpoint 46080) https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA

Also thanks to Meta for LLaMA.

Each model and LoRA was hand picked and considered for what it could contribute to this ensemble. Thanks to each and every one of you for your incredible work developing some of the best things to come out of this community.

Downloads last month: 1,146

Safetensors

Model size

33B params

Tensor type

F32

F16

Model tree for CalderaAI/30B-Lazarus

Quantizations

4 models

CalderaAI
/

30B-Lazarus

30B-Lazarus

Composition:

Language Models and LoRAs Used Credits:

Model tree for CalderaAI/30B-Lazarus

Spaces using CalderaAI/30B-Lazarus 40