Instructions to use Asilarkness/MetaCog-V2-300M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Asilarkness/MetaCog-V2-300M with Transformers:

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

pipe = pipeline("text-generation", model="Asilarkness/MetaCog-V2-300M", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Asilarkness/MetaCog-V2-300M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Asilarkness/MetaCog-V2-300M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Asilarkness/MetaCog-V2-300M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Asilarkness/MetaCog-V2-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Asilarkness/MetaCog-V2-300M

SGLang

How to use Asilarkness/MetaCog-V2-300M 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 "Asilarkness/MetaCog-V2-300M" \
    --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": "Asilarkness/MetaCog-V2-300M",
		"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 "Asilarkness/MetaCog-V2-300M" \
        --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": "Asilarkness/MetaCog-V2-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Asilarkness/MetaCog-V2-300M with Docker Model Runner:
```
docker model run hf.co/Asilarkness/MetaCog-V2-300M
```

MetaCog-V2-300M

MetaCog-V2 is a 301,268,512-parameter dialogue language model trained from scratch with Meta V2 explicit recurrent state: four levels, eight memory slots per level, learned read/write/erase, confidence and routing. The released inference export contains the SFT checkpoint at step 1526 (500,039,680 tokens).

Training

Pretraining: 6,500,188,160 tokens
SFT: 500,039,680 tokens
SFT carry validation: loss 1.6080, PPL 4.993
SFT reset validation: loss 1.6283, PPL 5.095

Evaluation

benchmarks/meta_sft_bench.json contains the exact run. Knowledge subset (50 examples/task): ARC-Easy 40.00%, HellaSwag 26.00%, Winogrande 52.00%, BoolQ 22.00%. The ordinary-attention control in the speed table is untrained; therefore no quality comparison to that control is claimed. Speed measurements use the same GPU and sequence length.

Loading

Install liger-kernel and load with trust_remote_code=True. Persistent state is available through forward_hidden(..., state=..., reset_mask=...); see chat.py.

Limitations

This is a research checkpoint. The short generation smoke test produced immediate stop outputs on the tested prompts; treat dialogue quality as experimental, not production-ready.

Downloads last month: -

Safetensors

Model size

0.3B params

Tensor type

BF16