Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 33
How to use Novaciano/HDP-1B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Novaciano/HDP-1B") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Novaciano/HDP-1B")
model = AutoModelForCausalLM.from_pretrained("Novaciano/HDP-1B")How to use Novaciano/HDP-1B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Novaciano/HDP-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Novaciano/HDP-1B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Novaciano/HDP-1B
How to use Novaciano/HDP-1B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Novaciano/HDP-1B" \
--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": "Novaciano/HDP-1B",
"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 "Novaciano/HDP-1B" \
--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": "Novaciano/HDP-1B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Novaciano/HDP-1B with Docker Model Runner:
docker model run hf.co/Novaciano/HDP-1B
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using Novaciano/Esperpento-1B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Novaciano/HDP-1B
parameters:
density: 0.38
weight: 0.55
- model: megabytes/gemma-3-1b-qat-int4-heretic
parameters:
density: 0.35
weight: 0.30
merge_method: dare_ties # Más agresivo que TIES puro
base_model: Novaciano/Esperpento-1B
parameters:
normalize: false
rescale: true # Amplifica bias NSFW
int8_mask: true
density: 0.38 # Baja para más filo
lambda: -0.45 # Suprime moral residual
dtype: float16