Instructions to use hazyresearch/based-360m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hazyresearch/based-360m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hazyresearch/based-360m")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hazyresearch/based-360m", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use hazyresearch/based-360m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hazyresearch/based-360m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hazyresearch/based-360m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hazyresearch/based-360m
- SGLang
How to use hazyresearch/based-360m 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 "hazyresearch/based-360m" \ --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": "hazyresearch/based-360m", "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 "hazyresearch/based-360m" \ --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": "hazyresearch/based-360m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hazyresearch/based-360m with Docker Model Runner:
docker model run hf.co/hazyresearch/based-360m
Improve model card: Add pipeline tag, library name and license (#4)
Browse files- Improve model card: Add pipeline tag, library name and license (0c71f837c680a8c706feea6d14df1d7347e7a96f)
Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -3,7 +3,11 @@ datasets:
|
|
| 3 |
- EleutherAI/pile
|
| 4 |
language:
|
| 5 |
- en
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
|
|
|
| 7 |
# Model Card
|
| 8 |
|
| 9 |
This model is pretrained Based model. Based is strong at recalling information provided in context, despite using a fixed amount of memory during inference.
|
|
@@ -40,4 +44,4 @@ Please consider citing this paper if you use our work:
|
|
| 40 |
}
|
| 41 |
```
|
| 42 |
|
| 43 |
-
Please reach out to simarora@stanford.edu, eyuboglu@stanford.edu, and mzhang20@stanford.edu with questions.
|
|
|
|
| 3 |
- EleutherAI/pile
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
library_name: transformers
|
| 8 |
+
license: mit
|
| 9 |
---
|
| 10 |
+
|
| 11 |
# Model Card
|
| 12 |
|
| 13 |
This model is pretrained Based model. Based is strong at recalling information provided in context, despite using a fixed amount of memory during inference.
|
|
|
|
| 44 |
}
|
| 45 |
```
|
| 46 |
|
| 47 |
+
Please reach out to simarora@stanford.edu, eyuboglu@stanford.edu, and mzhang20@stanford.edu with questions.
|