Instructions to use Ateron/Predonia-24B-V2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ateron/Predonia-24B-V2.1 with Transformers:

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

pipe = pipeline("text-generation", model="Ateron/Predonia-24B-V2.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ateron/Predonia-24B-V2.1")
model = AutoModelForCausalLM.from_pretrained("Ateron/Predonia-24B-V2.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ateron/Predonia-24B-V2.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ateron/Predonia-24B-V2.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ateron/Predonia-24B-V2.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ateron/Predonia-24B-V2.1

SGLang

How to use Ateron/Predonia-24B-V2.1 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 "Ateron/Predonia-24B-V2.1" \
    --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": "Ateron/Predonia-24B-V2.1",
		"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 "Ateron/Predonia-24B-V2.1" \
        --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": "Ateron/Predonia-24B-V2.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ateron/Predonia-24B-V2.1 with Docker Model Runner:
```
docker model run hf.co/Ateron/Predonia-24B-V2.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

PredoniaV2.1

This is different merge method and seems to have better performance.

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: E:\AI\Precog
    parameters:
      density: [1.0, 0.75, 0.50] # density gradient
      weight: 1.0
  - model: E:\AI\Cydonia 4.3
    parameters:
      density: 0.35
      weight: [0, 0.3, 0.4, 0.5] # weight gradient
merge_method: ties
base_model: E:\AI\Precog
parameters:
  normalize: true
  int8_mask: true
dtype: float16

Downloads last month: 5

Safetensors

Model size

24B params

Tensor type

F16

Model tree for Ateron/Predonia-24B-V2.1

TheDrummer/Cydonia-24B-v4.3

TheDrummer/Precog-24B-v1

Merge model

this model

Quantizations

2 models