Not-For-All-Audiences

Instructions to use ABX-AI/Quantum-Citrus-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ABX-AI/Quantum-Citrus-9B with Transformers:

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

pipe = pipeline("text-generation", model="ABX-AI/Quantum-Citrus-9B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ABX-AI/Quantum-Citrus-9B")
model = AutoModelForMultimodalLM.from_pretrained("ABX-AI/Quantum-Citrus-9B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ABX-AI/Quantum-Citrus-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ABX-AI/Quantum-Citrus-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ABX-AI/Quantum-Citrus-9B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ABX-AI/Quantum-Citrus-9B

SGLang

How to use ABX-AI/Quantum-Citrus-9B 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 "ABX-AI/Quantum-Citrus-9B" \
    --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": "ABX-AI/Quantum-Citrus-9B",
		"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 "ABX-AI/Quantum-Citrus-9B" \
        --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": "ABX-AI/Quantum-Citrus-9B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ABX-AI/Quantum-Citrus-9B with Docker Model Runner:
```
docker model run hf.co/ABX-AI/Quantum-Citrus-9B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Quantum-Citrus-9B

This merge is another attempt at making and intelligent, refined and unaligned model.

Based on my tests so far, it has accomplished the goals, and I am continuing to experiment with my interactions with it.

It includes previous merges of Starling, Cerebrum, LemonadeRP, InfinityRP, and deep down has a base of layla v0.1, as I am not that happy with the result form using v0.2.

The model is intended for fictional storytelling and roleplaying and may not be intended for all audences.

GGUF / IQ / Imatrix

Merge Details

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

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

ABX-AI/Starfinite-Laymospice-v2-7B
ABX-AI/Cerebral-Infinity-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: ABX-AI/Cerebral-Infinity-7B
        layer_range: [0, 20]
  - sources:
      - model: ABX-AI/Starfinite-Laymospice-v2-7B
        layer_range: [12, 32]
merge_method: passthrough
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	66.74
AI2 Reasoning Challenge (25-Shot)	65.19
HellaSwag (10-Shot)	84.75
MMLU (5-Shot)	64.58
TruthfulQA (0-shot)	55.96
Winogrande (5-shot)	79.40
GSM8k (5-shot)	50.57