Instructions to use backyardai/Psyonic-Cetacean-32bit-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use backyardai/Psyonic-Cetacean-32bit-20B with Transformers:

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

pipe = pipeline("text-generation", model="backyardai/Psyonic-Cetacean-32bit-20B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("backyardai/Psyonic-Cetacean-32bit-20B")
model = AutoModelForCausalLM.from_pretrained("backyardai/Psyonic-Cetacean-32bit-20B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use backyardai/Psyonic-Cetacean-32bit-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "backyardai/Psyonic-Cetacean-32bit-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "backyardai/Psyonic-Cetacean-32bit-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/backyardai/Psyonic-Cetacean-32bit-20B

SGLang

How to use backyardai/Psyonic-Cetacean-32bit-20B 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 "backyardai/Psyonic-Cetacean-32bit-20B" \
    --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": "backyardai/Psyonic-Cetacean-32bit-20B",
		"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 "backyardai/Psyonic-Cetacean-32bit-20B" \
        --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": "backyardai/Psyonic-Cetacean-32bit-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use backyardai/Psyonic-Cetacean-32bit-20B with Docker Model Runner:
```
docker model run hf.co/backyardai/Psyonic-Cetacean-32bit-20B
```

Psyonic-Cetacean-32bit-20B

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: TeeZee/Orca-2-13b_flat
      layer_range: [0, 16]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Psyfighter2
      layer_range: [8, 24]
  - sources:
    - model: TeeZee/Orca-2-13b_flat
      layer_range: [17, 32]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Psyfighter2
      layer_range: [25, 40]
merge_method: passthrough
dtype: float32

Downloads last month: 9

Safetensors

Model size

20B params

Tensor type

F32

Model tree for backyardai/Psyonic-Cetacean-32bit-20B

KoboldAI/LLaMA2-13B-Psyfighter2

TeeZee/Orca-2-13b_flat

Merge model

this model

Merges

2 models