Instructions to use gpjt/8xa100m80 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gpjt/8xa100m80 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="gpjt/8xa100m80", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("gpjt/8xa100m80", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use gpjt/8xa100m80 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gpjt/8xa100m80" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gpjt/8xa100m80", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/gpjt/8xa100m80
- SGLang
How to use gpjt/8xa100m80 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 "gpjt/8xa100m80" \ --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": "gpjt/8xa100m80", "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 "gpjt/8xa100m80" \ --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": "gpjt/8xa100m80", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use gpjt/8xa100m80 with Docker Model Runner:
docker model run hf.co/gpjt/8xa100m80
Update README.md
Browse files
README.md
CHANGED
|
@@ -84,6 +84,7 @@ number of tokens. It's [both dumb and ignorant](https://www.gilesthomas.com/202
|
|
| 84 |
- **Micro-batch size:** 28
|
| 85 |
- **Global batch size:** 224
|
| 86 |
- **Dropout:** 0.1
|
|
|
|
| 87 |
- **Learning rate:** 0.0004
|
| 88 |
- **Schedule learning rate:** False
|
| 89 |
- **Weight decay:** 0.1
|
|
|
|
| 84 |
- **Micro-batch size:** 28
|
| 85 |
- **Global batch size:** 224
|
| 86 |
- **Dropout:** 0.1
|
| 87 |
+
- **Gradient clipping**: None
|
| 88 |
- **Learning rate:** 0.0004
|
| 89 |
- **Schedule learning rate:** False
|
| 90 |
- **Weight decay:** 0.1
|