Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 33
How to use yuuko-eth/Monsoon-7B-exp-1 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="yuuko-eth/Monsoon-7B-exp-1") # Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM
tokenizer = AutoTokenizer.from_pretrained("yuuko-eth/Monsoon-7B-exp-1")
model = AutoModelForMultimodalLM.from_pretrained("yuuko-eth/Monsoon-7B-exp-1")How to use yuuko-eth/Monsoon-7B-exp-1 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuuko-eth/Monsoon-7B-exp-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "yuuko-eth/Monsoon-7B-exp-1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/yuuko-eth/Monsoon-7B-exp-1
How to use yuuko-eth/Monsoon-7B-exp-1 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "yuuko-eth/Monsoon-7B-exp-1" \
--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": "yuuko-eth/Monsoon-7B-exp-1",
"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 "yuuko-eth/Monsoon-7B-exp-1" \
--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": "yuuko-eth/Monsoon-7B-exp-1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use yuuko-eth/Monsoon-7B-exp-1 with Docker Model Runner:
docker model run hf.co/yuuko-eth/Monsoon-7B-exp-1
Breeze 7B Instruct 與 Silicon-Maid-7B (角扮用) 的 dare-ties merge 試驗性模型。
請用 Silicon-Maid-7B 或是 Breeze-7B-Instruct 所推薦的 Prompt 格式進行操作;以下為模型配置。
This is an experimental Mistral-architecture DARE-TIES merge model of 2x 7B sized fine-tunes. Breeze and Silicon Maid are used together.
Model configuration is as follows:
To use the model, please use either prompt templates suggested by the base models.