Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 33
How to use from
SGLangUse 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 "jeiku/Weekend_Project" \
--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": "jeiku/Weekend_Project",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Weekend
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using ResplendentAI/Paradigm_7B as a base.
Models Merged
The following models were included in the merge:
- ResplendentAI/Paradigm_7B + jeiku/Theory_of_Mind_Roleplay_Mistral
- ResplendentAI/Paradigm_7B + jeiku/Theory_of_Mind_Mistral
Configuration
The following YAML configuration was used to produce this model:
merge_method: dare_ties
base_model: ResplendentAI/Paradigm_7B
parameters:
normalize: true
models:
- model: ResplendentAI/Paradigm_7B+jeiku/Theory_of_Mind_Roleplay_Mistral
parameters:
weight: 1
- model: ResplendentAI/Paradigm_7B+jeiku/Theory_of_Mind_Mistral
parameters:
weight: 1
dtype: float16
- Downloads last month
- 8
Model tree for jeiku/Weekend_Project
Merge model
this model
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "jeiku/Weekend_Project" \ --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": "jeiku/Weekend_Project", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'