Instructions to use denru/Luminum-v0.1-123B-5_5bpw-h6-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use denru/Luminum-v0.1-123B-5_5bpw-h6-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="denru/Luminum-v0.1-123B-5_5bpw-h6-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("denru/Luminum-v0.1-123B-5_5bpw-h6-exl2")
model = AutoModelForCausalLM.from_pretrained("denru/Luminum-v0.1-123B-5_5bpw-h6-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use denru/Luminum-v0.1-123B-5_5bpw-h6-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "denru/Luminum-v0.1-123B-5_5bpw-h6-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "denru/Luminum-v0.1-123B-5_5bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/denru/Luminum-v0.1-123B-5_5bpw-h6-exl2

SGLang

How to use denru/Luminum-v0.1-123B-5_5bpw-h6-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 "denru/Luminum-v0.1-123B-5_5bpw-h6-exl2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "denru/Luminum-v0.1-123B-5_5bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "denru/Luminum-v0.1-123B-5_5bpw-h6-exl2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "denru/Luminum-v0.1-123B-5_5bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use denru/Luminum-v0.1-123B-5_5bpw-h6-exl2 with Docker Model Runner:
```
docker model run hf.co/denru/Luminum-v0.1-123B-5_5bpw-h6-exl2
```

Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

LuminumMistral-123B

Overview

I present Luminum-123B.

This is a merge using Mistral Large as a base, and including Lumimaid-v0.2-123B and Magnum-v2-123B. I felt like Magnum was rambling too much, and Lumimaid lost slightly too much brain power, so I used Mistral Large base for a long while, but it was lacking some moist.

On a whim, I decided to merge both Lumimaid and Magnum on top of Mistral large, and while I wasn't expecting much, I've been very surprised with the results. I've found that this model keeps the brain power from Mistral base, and also inherits the lexique of Lumimaid and creative descriptions of Magnum, without rambling too much.

I've tested this model quite extensively at and above 32k with great success. It should in theory allow for the full 128k context, albeit I've only went to 40-50k max. It's become my new daily driver.

The only negative thing I could find is that it tends to generate long responses if you let it. It probably gets that from Magnum. Just don't let it grow its answer size over and over.

I recommend thoses settings:

Minp: 0.08
Rep penalty: 1.03
Rep penalty range : 4096
Smoothing factor: 0.23
No Repeat NGram Size: 2 *

*I didn't get the chance to mess with DRY yet.

Template

All the merged models use Mistral template, this one too.

<s>[INST] {input} [/INST] {output}</s>

Quants

GGUF

Static quants

EXL2

4.0bpw

Merge Method

This model was merged using the della_linear merge method using mistralaiMistral-Large-Instruct-2407 as a base.

Models Merged

The following models were included in the merge:

NeverSleepLumimaid-v0.2-123B
anthracite-orgmagnum-v2-123b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: anthracite-orgmagnum-v2-123b
    parameters:
      weight: 0.19
      density: 0.5
  - model: NeverSleepLumimaid-v0.2-123B
    parameters:
      weight: 0.34
      density: 0.8
merge_method: della_linear
base_model: mistralaiMistral-Large-Instruct-2407
parameters:
  epsilon: 0.05
  lambda: 1
  int8_mask: true
dtype: bfloat16

Downloads last month: 4