mag-pe
Collection
ONLY TESTED FOR COHERENCY. Attempts to merge MN-12B-Mag-Mell-R1 with Dans-PersonalityEngine-V1.3.0-12b, in an attempt to improve writing. • 2 items • Updated
How to use Snqwii/mag-pe-dt with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Snqwii/mag-pe-dt") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Snqwii/mag-pe-dt")
model = AutoModelForCausalLM.from_pretrained("Snqwii/mag-pe-dt", device_map="auto")How to use Snqwii/mag-pe-dt with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Snqwii/mag-pe-dt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Snqwii/mag-pe-dt",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Snqwii/mag-pe-dt
How to use Snqwii/mag-pe-dt with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Snqwii/mag-pe-dt" \
--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": "Snqwii/mag-pe-dt",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "Snqwii/mag-pe-dt" \
--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": "Snqwii/mag-pe-dt",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Snqwii/mag-pe-dt with Docker Model Runner:
docker model run hf.co/Snqwii/mag-pe-dt
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using mistralai/Mistral-Nemo-Base-2407 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
name: Mags-PersonalityEngine
merge_method: dare_ties
base_model: mistralai/Mistral-Nemo-Base-2407
models:
- model: PocketDoc/Dans-PersonalityEngine-V1.3.0-12b
parameters:
weight: 1
density: 0.9
- model: inflatebot/MN-12B-Mag-Mell-R1
parameters:
weight: 0.5
density: 0.7