Instructions to use seb-c/Psydestroyer-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use seb-c/Psydestroyer-20B with Transformers:

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

pipe = pipeline("text-generation", model="seb-c/Psydestroyer-20B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("seb-c/Psydestroyer-20B")
model = AutoModelForMultimodalLM.from_pretrained("seb-c/Psydestroyer-20B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use seb-c/Psydestroyer-20B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/seb-c/Psydestroyer-20B

SGLang

How to use seb-c/Psydestroyer-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 "seb-c/Psydestroyer-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": "seb-c/Psydestroyer-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 "seb-c/Psydestroyer-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": "seb-c/Psydestroyer-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use seb-c/Psydestroyer-20B with Docker Model Runner:
```
docker model run hf.co/seb-c/Psydestroyer-20B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Psydestroyer 20B

I self-merged KoboldAI's Psyfighter-13B to get a 20B model, hoping to make it smarter.

GGUFs: https://huggingface.co/seb-c/Psydestroyer-20B-GGUF I have only made a Q4_K_M as that is what I tend to use when running 20Bs on my 3060 12GB, but if the demand is there I can make more.

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:

KoboldAI/LLaMA2-13B-Psyfighter2

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: "KoboldAI/LLaMA2-13B-Psyfighter2"
      layer_range: [0, 16]
  - sources:
    - model: "KoboldAI/LLaMA2-13B-Psyfighter2"
      layer_range: [8, 24]
  - sources:
    - model: "KoboldAI/LLaMA2-13B-Psyfighter2"
      layer_range: [17, 32]
  - sources:
    - model: "KoboldAI/LLaMA2-13B-Psyfighter2"
      layer_range: [25, 40]
merge_method: passthrough
dtype: float16

Downloads last month: 92

Safetensors

Model size

20B params

Tensor type

F16

Model tree for seb-c/Psydestroyer-20B

Base model

KoboldAI/LLaMA2-13B-Psyfighter2

Finetuned

(2)

this model

Merges

3 models

Quantizations

1 model