Instructions to use digitous/Alpacino13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitous/Alpacino13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="digitous/Alpacino13b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("digitous/Alpacino13b") model = AutoModelForCausalLM.from_pretrained("digitous/Alpacino13b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use digitous/Alpacino13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "digitous/Alpacino13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/Alpacino13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/digitous/Alpacino13b
- SGLang
How to use digitous/Alpacino13b 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 "digitous/Alpacino13b" \ --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": "digitous/Alpacino13b", "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 "digitous/Alpacino13b" \ --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": "digitous/Alpacino13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use digitous/Alpacino13b with Docker Model Runner:
docker model run hf.co/digitous/Alpacino13b
Commit History
-
Update README.md
7092a5c
-
Upload 4bit.safetensors
378c2d8 -
Update README.md
65e9a9a
-
Update README.md
b04db99 -
Update README.md
3814b73 -
Update README.md
796e6e9 -
Update README.md
f5d6a96 -
Update README.md
219020b -
Update README.md
be88d51 -
Update README.md
cfd5aea -
Update README.md
de4890f -
Update README.md
b7ca89b -
Update README.md
539f5f0 -
Update README.md
add54eb -
Update README.md
39521fd -
Update README.md
ef94bd5 -
Update README.md
a674a99 -
Update README.md
f493b18 -
Update README.md
1e2b7ac -
Update README.md
f23e899 -
Update README.md
df126f7 -
Upload 19 files
A Llama model merge implementing Chain of Thought and Storytelling, with a backbone of Alpaca Instructions. Mainly censorship free, intended for hobbyists, researchers, and those who want an infinite text based adventure. Likely also perfect as a chatbot. Tailor the following instruct example to your preference and insert it into your interface's memory/context of choice to have it function as you wish; this example uses chat mode with a bot named Narrator assigned a text adventure role and Player the text input role - ### Instruction: Make Narrator function as a text based adventure game that responds with verbose, detailed, and creative descriptions of what happens next after Player's response. Make Player function as the player input for Narrator's text based adventure game, controlling a character named [insert character's name, short bio, and story situation to remain consistent in memory]. ### Response: Recommended presets present in KoboldAI & Text-Generation-WebUI: Storywrit…89735ad -
initial commit
00ba0e1