Instructions to use BrainChip-AI/tenns-llm-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BrainChip-AI/tenns-llm-1b with Transformers:

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

pipe = pipeline("text-generation", model="BrainChip-AI/tenns-llm-1b", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BrainChip-AI/tenns-llm-1b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BrainChip-AI/tenns-llm-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BrainChip-AI/tenns-llm-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BrainChip-AI/tenns-llm-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BrainChip-AI/tenns-llm-1b

SGLang

How to use BrainChip-AI/tenns-llm-1b 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 "BrainChip-AI/tenns-llm-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": "BrainChip-AI/tenns-llm-1b",
		"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 "BrainChip-AI/tenns-llm-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": "BrainChip-AI/tenns-llm-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BrainChip-AI/tenns-llm-1b with Docker Model Runner:
```
docker model run hf.co/BrainChip-AI/tenns-llm-1b
```

@@ -99,3 +99,8 @@ LoRA adapters are merged into base weights at export time.
 - English only
 - No system prompt or chat template — plain completion model
 - Recurrent state resets between calls to `generate_text()`

 - English only
 - No system prompt or chat template — plain completion model
 - Recurrent state resets between calls to `generate_text()`
+## Source Code
+- Inference script and model definition: [Brainchip-Inc/tenns_llm](https://github.com/Brainchip-Inc/tenns_llm)
+- Underlying SSM layer library: [Brainchip-Inc/tenns-core](https://github.com/Brainchip-Inc/tenns-core)

Duplicated from NickMarkovsky/tenns-llm-1b

BrainChip-AI
/

tenns-llm-1b

Repo hygiene: remove pycache bytecode, link GitHub source repos

Repo hygiene: remove __pycache__ bytecode, link GitHub source repos

Repo hygiene: remove pycache bytecode, link GitHub source repos