Instructions to use jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6")

# Load model directly
from transformers import AutoTokenizer, LlamaForCausalLM_sharedHyper

tokenizer = AutoTokenizer.from_pretrained("jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6")
model = LlamaForCausalLM_sharedHyper.from_pretrained("jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6

SGLang

How to use jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6" \
    --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": "jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use 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 "jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6" \
        --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": "jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6 with Docker Model Runner:
```
docker model run hf.co/jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6
```

MeGan (meta_swiglu) - CrossFit & UnifiedQA SFT

This model is a fine-tuned version of Llama-3.1-8B-Instruct implementing the meta-gating mechanism proposed in Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM.

GitHub Repository: MeGan
Dataset: CrossFit and UnifiedQA (Hugging Face Dataset)

Model description

Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. This work activates the meta-signal of $\beta$ within the SwiGLU blocks, resulting in a meta-gating mechanism that adaptively adjusts the nonlinearity of FFN. A hypernetwork is employed which dynamically produces $\beta$ on textual conditions, providing meta-controllability on LLMs.

This checkpoint is trained on a subset (non_nli_to_nli) of CrossFit and UnifiedQA.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 32
total_train_batch_size: 32
total_eval_batch_size: 256
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1.0

Framework versions

Transformers 4.46.1
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.20.3

Citation

If you find this work useful, please consider citing:

@article{ji2026learntolearn,
  title={Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM},
  author={Luo Ji and Qi Qin and Ningyuan Xi and Teng Chen and Qingqing Gu and Hongyan Li},
  journal={arXiv preprint arXiv:2605.01973},
  year={2026}
}

Downloads last month: 79

Paper for jiluoaaron/MeGan-R512-CrossFit_UnifiedQA-nn2n-lr1e-6

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

Paper • 2605.01973 • Published May 3