Instructions to use MK0727/lambda-1-160m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MK0727/lambda-1-160m-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MK0727/lambda-1-160m-base")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MK0727/lambda-1-160m-base", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MK0727/lambda-1-160m-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MK0727/lambda-1-160m-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MK0727/lambda-1-160m-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MK0727/lambda-1-160m-base
- SGLang
How to use MK0727/lambda-1-160m-base 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 "MK0727/lambda-1-160m-base" \ --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": "MK0727/lambda-1-160m-base", "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 "MK0727/lambda-1-160m-base" \ --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": "MK0727/lambda-1-160m-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MK0727/lambda-1-160m-base with Docker Model Runner:
docker model run hf.co/MK0727/lambda-1-160m-base
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,19 @@ The model was pretrained on a Japanese text mixture.
|
|
| 39 |
| `MK0727/CleanedFineWeb2Edu-jp` | Filtered Japanese web corpus |
|
| 40 |
| `MK0727/SyntheticTextbook-jp` | Synthetic Japanese corpus |
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
## Limitations
|
| 44 |
|
|
|
|
| 39 |
| `MK0727/CleanedFineWeb2Edu-jp` | Filtered Japanese web corpus |
|
| 40 |
| `MK0727/SyntheticTextbook-jp` | Synthetic Japanese corpus |
|
| 41 |
|
| 42 |
+
## Usage
|
| 43 |
+
```bash
|
| 44 |
+
git clone https://github.com/KeisukeMiyamoto1324/lambda.git
|
| 45 |
+
cd lambda
|
| 46 |
+
python3 -m venv venv
|
| 47 |
+
source venv/bin/activate
|
| 48 |
+
pip3 install -r requirements.txt
|
| 49 |
+
|
| 50 |
+
python3 src/inference_base/inference_hf.py \
|
| 51 |
+
--prompt "人工知能とは" \
|
| 52 |
+
--max-new-tokens 64
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
|
| 56 |
## Limitations
|
| 57 |
|