Instructions to use taozi555/412mixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use taozi555/412mixed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="taozi555/412mixed")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("taozi555/412mixed") model = AutoModelForCausalLM.from_pretrained("taozi555/412mixed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use taozi555/412mixed with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "taozi555/412mixed" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "taozi555/412mixed", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/taozi555/412mixed
- SGLang
How to use taozi555/412mixed 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 "taozi555/412mixed" \ --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": "taozi555/412mixed", "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 "taozi555/412mixed" \ --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": "taozi555/412mixed", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use taozi555/412mixed with Docker Model Runner:
docker model run hf.co/taozi555/412mixed
update
Browse files- .ipynb_checkpoints/README-checkpoint.md +0 -0
- README.md +0 -43
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
File without changes
|
README.md
CHANGED
|
@@ -1,43 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
pipeline_tag: text-generation
|
| 4 |
-
tags:
|
| 5 |
-
- safetensors
|
| 6 |
-
- mistral
|
| 7 |
-
- not-for-all-audiences
|
| 8 |
-
- nsfw
|
| 9 |
-
- rp
|
| 10 |
-
- roleplay
|
| 11 |
-
language:
|
| 12 |
-
- en
|
| 13 |
-
---
|
| 14 |
-

|
| 15 |
-
|
| 16 |
-
This is an experimental model I currently use. It's far from great as I'm still working on it, but I leave it here for people to try if interested in this format.
|
| 17 |
-
This model was basically made to stop some upsetting hallucinations, so {{char}} mostly and occasionally will wait {{user}} response instead of responding itself or deciding for {{user}}, also, my primary idea was to create a cozy model that thinks.*
|
| 18 |
-
|
| 19 |
-
Inspired by [lemonilia/Limamono-Mistral-7B-v0.50](https://huggingface.co/lemonilia/Limamono-Mistral-7B-v0.50)
|
| 20 |
-
### Style details:
|
| 21 |
-
- Quotes are used for character dialogs.
|
| 22 |
-
- `"Hey, Anon... What do you think about my style?"`
|
| 23 |
-
- Asterisks can be used for narration, but it's optional, it's recommended to use default novel format.
|
| 24 |
-
- `*Her cheeks blush slightly, she tries to hide.*`
|
| 25 |
-
- Character thoughts are wrapped with ` marks. **This may often spontaneously occur.**
|
| 26 |
-
- `My heart skips a beat hearing him call me pretty!`
|
| 27 |
-
|
| 28 |
-
*If you want thoughts to appear more often, just add something like this to your system prompt: ```"{{char}} internal thoughts are wrapped with ` marks."```*
|
| 29 |
-
|
| 30 |
-
- Accepted response lengths: ***tiny, short, medium, long, huge***
|
| 31 |
-
-
|
| 32 |
-
For example: ### Response: (length = medium)
|
| 33 |
-
|
| 34 |
-
Note: Apparently ***humongous***, ***extreme*** and ***unlimited*** may not work at moment. Not fully tested.
|
| 35 |
-
|
| 36 |
-
### Prompt format:
|
| 37 |
-
Extended Alpaca, as always.
|
| 38 |
-
|
| 39 |
-
``"You are now in roleplay chat mode. Engage in an endless chat with {{user}}. Always wait {{user}} turn, next actions and responses."``
|
| 40 |
-
|
| 41 |
-
## Example:
|
| 42 |
-
|
| 43 |
-

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|