Instructions to use MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8 with Transformers:

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

pipe = pipeline("text-generation", model="MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8")
model = AutoModelForCausalLM.from_pretrained("MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8")
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 MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8

SGLang

How to use MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8 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 "MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8" \
    --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": "MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8",
		"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 "MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8" \
        --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": "MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8 with Docker Model Runner:
```
docker model run hf.co/MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8
```

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

Quantized using the default exllamav3 (0.0.1) quantization process.

Original model: https://huggingface.co/knifeayumu/Cydonia-v1.3-Magnum-v4-22B
exllamav3: https://github.com/turboderp-org/exllamav3

The Drummer becomes hornier (again)

Recipe based on knifeayumu/Cydonia-v1.2-Magnum-v4-22B but uses TheDrummer/Cydonia-22B-v1.3 as the base. Yes, MortalWombat. I'm gonna use your parameters as long as I can!

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/Cydonia-22B-v1.3
  - model: anthracite-org/magnum-v4-22b
merge_method: slerp
base_model: TheDrummer/Cydonia-22B-v1.3
parameters:
  t: [0.1, 0.3, 0.6, 0.3, 0.1]
dtype: bfloat16

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

F16

I16

Model tree for MetaphoricalCode/Cydonia-v1.3-Magnum-v4-22B-exl3-6.5bpw-hb8

Base model

knifeayumu/Cydonia-v1.3-Magnum-v4-22B

Quantized

(20)

this model