Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 33
How to use jeiku/Test25_3B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="jeiku/Test25_3B", trust_remote_code=True)
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jeiku/Test25_3B", trust_remote_code=True, dtype="auto")How to use jeiku/Test25_3B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeiku/Test25_3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "jeiku/Test25_3B",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/jeiku/Test25_3B
How to use jeiku/Test25_3B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "jeiku/Test25_3B" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "jeiku/Test25_3B",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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/Test25_3B" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "jeiku/Test25_3B",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use jeiku/Test25_3B with Docker Model Runner:
docker model run hf.co/jeiku/Test25_3B
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using jeiku/Bones_3B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: jeiku/Bones_3B+jeiku/Toxic_DPO_StableLM
parameters:
weight: 0.25
density: 1
- model: jeiku/Bones_3B+jeiku/No_Robots_Alpaca_StableLM
parameters:
weight: 0.25
density: 1
- model: jeiku/Bones_3B
parameters:
weight: 0.50
density: 1
merge_method: dare_ties
base_model: jeiku/Bones_3B
parameters:
dtype: bfloat16
docker model run hf.co/jeiku/Test25_3B