Instructions to use JimK28/moe-causal-top2-generalist with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JimK28/moe-causal-top2-generalist with Transformers:

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

pipe = pipeline("text-generation", model="JimK28/moe-causal-top2-generalist", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("JimK28/moe-causal-top2-generalist", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JimK28/moe-causal-top2-generalist with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JimK28/moe-causal-top2-generalist"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JimK28/moe-causal-top2-generalist",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JimK28/moe-causal-top2-generalist

SGLang

How to use JimK28/moe-causal-top2-generalist 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 "JimK28/moe-causal-top2-generalist" \
    --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": "JimK28/moe-causal-top2-generalist",
		"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 "JimK28/moe-causal-top2-generalist" \
        --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": "JimK28/moe-causal-top2-generalist",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JimK28/moe-causal-top2-generalist with Docker Model Runner:
```
docker model run hf.co/JimK28/moe-causal-top2-generalist
```

moe-causal-top2-generalist

BabyLM 2026 Strict-Small submission (NTUA). A shared-generalist Mixture-of-Experts language model: decoder-only causal MoE — hidden 512, 12 layers, all-MoE with an always-on generalist FFN (size 1024) + 15 routed specialists (size 256), top-2 softmax routing.

Training data: BabyLM-community/BabyLM-2026-Strict-Small (≤100M words, counting repeated exposures, per CfP §4.2). Uniform ~10 passes via bin-packing (each segment once per epoch).
Objective: causal (next-token) LM. Evaluate with the causal backend.
Intermediate checkpoints: available as branches chck_1M … chck_100M (words seen), per the BabyLM checkpoint convention.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
tok = AutoTokenizer.from_pretrained("JimK28/moe-causal-top2-generalist", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("JimK28/moe-causal-top2-generalist", trust_remote_code=True)

Custom architecture — trust_remote_code=True is required (config auto_map points at modeling_moe_causal). Trained with the NTUA BabyLM pipeline (https://github.com/emhadzi/BabyLM).

Downloads last month: 216

JimK28
/

moe-causal-top2-generalist

moe-causal-top2-generalist

Usage

Dataset used to train JimK28/moe-causal-top2-generalist