Instructions to use vtava/TinyCeNN-LM-Distilled-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vtava/TinyCeNN-LM-Distilled-v2 with Transformers:

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

pipe = pipeline("text-generation", model="vtava/TinyCeNN-LM-Distilled-v2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vtava/TinyCeNN-LM-Distilled-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vtava/TinyCeNN-LM-Distilled-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vtava/TinyCeNN-LM-Distilled-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vtava/TinyCeNN-LM-Distilled-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vtava/TinyCeNN-LM-Distilled-v2

SGLang

How to use vtava/TinyCeNN-LM-Distilled-v2 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 "vtava/TinyCeNN-LM-Distilled-v2" \
    --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": "vtava/TinyCeNN-LM-Distilled-v2",
		"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 "vtava/TinyCeNN-LM-Distilled-v2" \
        --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": "vtava/TinyCeNN-LM-Distilled-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vtava/TinyCeNN-LM-Distilled-v2 with Docker Model Runner:
```
docker model run hf.co/vtava/TinyCeNN-LM-Distilled-v2
```

TinyCeNN-LM Distilled v2

Transformer-free CeNN student distilled from arnir0/Tiny-LLM.

Architecture

Transformer layers remaining: 0
CeNN recurrent steps: 7
CeNN receptive field: 255 tokens
Trainable CeNN parameters: 480,192

Rigorous benchmark

Protocol: rigorous-v2
Deterministic held-out tokens: 65,536
Benchmark SHA256: 319c4527bb6a104bdd3772f30204fc8c32521f355f57d7c7fd387dbb058c3021
Cumulative distillation tokens: 40,005,632
Best student CE: 5.122586
Teacher CE: 4.234912
Best student PPL: 167.769
Teacher PPL: 69.056
Teacher-gap recovery: 84.42%

Load via tinycenn_lm.build_cenn_student().

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for vtava/TinyCeNN-LM-Distilled-v2

Base model

arnir0/Tiny-LLM

Finetuned

(10)

this model