Instructions to use allura-org/MS3-24B-Roselily-Creative with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allura-org/MS3-24B-Roselily-Creative with Transformers:

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

pipe = pipeline("text-generation", model="allura-org/MS3-24B-Roselily-Creative")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allura-org/MS3-24B-Roselily-Creative")
model = AutoModelForCausalLM.from_pretrained("allura-org/MS3-24B-Roselily-Creative", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use allura-org/MS3-24B-Roselily-Creative with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allura-org/MS3-24B-Roselily-Creative"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allura-org/MS3-24B-Roselily-Creative",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/allura-org/MS3-24B-Roselily-Creative

SGLang

How to use allura-org/MS3-24B-Roselily-Creative 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 "allura-org/MS3-24B-Roselily-Creative" \
    --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": "allura-org/MS3-24B-Roselily-Creative",
		"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 "allura-org/MS3-24B-Roselily-Creative" \
        --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": "allura-org/MS3-24B-Roselily-Creative",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use allura-org/MS3-24B-Roselily-Creative with Docker Model Runner:
```
docker model run hf.co/allura-org/MS3-24B-Roselily-Creative
```

ToastyPigeon commited on Feb 28, 2025

Commit

d3846c0

verified ·

1 Parent(s): a1252d4

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -16,6 +16,7 @@ make a model card and put a cute girl on it
 Making this public so it can be tried and possibly merged if desired while I work on getting the energy to write a proper card.
 Short list of things to know:
 - Instruct format: ChatML or Alpaca preferred, Tekken v7 possible
 - ChatML tokens were assigned to unused tokens 20 and 21, this leaves all the tekken tokens intact so merges w/ tekken models are feasible
 - Instruct-tuning phase did include Tekken v7 so the tokens are initialized and recognized, but I did not continue with it on the creative step because I do not like it for creative stuff (too restrictive with turn order)

 Making this public so it can be tried and possibly merged if desired while I work on getting the energy to write a proper card.
 Short list of things to know:
+- This is a bunch of RP, story writing, etc. creative data applied to [ToastyPigeon/ms3-roselily-instruct](https://huggingface.co/ToastyPigeon/ms3-roselily-instruct).
 - Instruct format: ChatML or Alpaca preferred, Tekken v7 possible
 - ChatML tokens were assigned to unused tokens 20 and 21, this leaves all the tekken tokens intact so merges w/ tekken models are feasible
 - Instruct-tuning phase did include Tekken v7 so the tokens are initialized and recognized, but I did not continue with it on the creative step because I do not like it for creative stuff (too restrictive with turn order)