Instructions to use PocketDoc/Dans-PersonalityEngine-V1.2.0-24b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PocketDoc/Dans-PersonalityEngine-V1.2.0-24b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="PocketDoc/Dans-PersonalityEngine-V1.2.0-24b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("PocketDoc/Dans-PersonalityEngine-V1.2.0-24b") model = AutoModelForCausalLM.from_pretrained("PocketDoc/Dans-PersonalityEngine-V1.2.0-24b") 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use PocketDoc/Dans-PersonalityEngine-V1.2.0-24b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "PocketDoc/Dans-PersonalityEngine-V1.2.0-24b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "PocketDoc/Dans-PersonalityEngine-V1.2.0-24b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
- SGLang
How to use PocketDoc/Dans-PersonalityEngine-V1.2.0-24b 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 "PocketDoc/Dans-PersonalityEngine-V1.2.0-24b" \ --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": "PocketDoc/Dans-PersonalityEngine-V1.2.0-24b", "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 "PocketDoc/Dans-PersonalityEngine-V1.2.0-24b" \ --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": "PocketDoc/Dans-PersonalityEngine-V1.2.0-24b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use PocketDoc/Dans-PersonalityEngine-V1.2.0-24b with Docker Model Runner:
docker model run hf.co/PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
Your model is amazing my dood.
I've been trying out a lot of models, and you've got a good one here. I see a lot of people post in Sally Tavern about these off situations and jokes that only Claude or other AIs can do. And I can assure you, your AI is currently taking scenarios with me and referencing them multiple prompts later with inside jokes, understanding that it's making humor on a meta level. Good fucking work.
This may be coming out of no where, but fuck it here it goes. I don't have a lot (any experience) but I do have a lot of time and drive to learn. I've recently read about MCP (I know it's been out a while but with OpenAI teaming up with Claude to standardize it, now feels like the right time) And I really want to take advantage of MCP, especially with your excellent model. Is there any way I can assist you with the project? If only a little? Obviously I'd want to get MCP working with the model, but, really, I just want to help make it better and expand it for people.
Anyways, figured I'd shoot my shot in the dark. Thank you for your work, and your dedication to the community.
Not only is it really good at following character sheets, it's also emotionally intelligent while remaining neutral enough to steer the conversation in either direction. What this means is that depending on the scenario, it won't hesitate to tell you off or be mean, but also can be supportive and positive. This is a perfect model for bouncing off ideas, soul-searching, or just plain old RP. Amazing indeed.