Instructions to use tokeron/TRBLLmaker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tokeron/TRBLLmaker with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tokeron/TRBLLmaker")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tokeron/TRBLLmaker") model = AutoModelForCausalLM.from_pretrained("tokeron/TRBLLmaker") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tokeron/TRBLLmaker with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tokeron/TRBLLmaker" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tokeron/TRBLLmaker", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tokeron/TRBLLmaker
- SGLang
How to use tokeron/TRBLLmaker 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 "tokeron/TRBLLmaker" \ --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": "tokeron/TRBLLmaker", "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 "tokeron/TRBLLmaker" \ --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": "tokeron/TRBLLmaker", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tokeron/TRBLLmaker with Docker Model Runner:
docker model run hf.co/tokeron/TRBLLmaker
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 508, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.740157480314961e-05, | |
| "loss": 2.7781, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.4874660477958952, | |
| "eval_loss": 2.6284313201904297, | |
| "eval_runtime": 69.4322, | |
| "eval_samples_per_second": 14.705, | |
| "eval_steps_per_second": 1.844, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.4803149606299215e-05, | |
| "loss": 2.6217, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.49078252111331633, | |
| "eval_loss": 2.6022448539733887, | |
| "eval_runtime": 70.8747, | |
| "eval_samples_per_second": 14.406, | |
| "eval_steps_per_second": 1.806, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.220472440944882e-05, | |
| "loss": 2.569, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.49170738058924846, | |
| "eval_loss": 2.5927629470825195, | |
| "eval_runtime": 76.8807, | |
| "eval_samples_per_second": 13.28, | |
| "eval_steps_per_second": 1.665, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 508, | |
| "total_flos": 3.0193916980494336e+16, | |
| "train_loss": 2.6286109864242433, | |
| "train_runtime": 3384.5609, | |
| "train_samples_per_second": 4.803, | |
| "train_steps_per_second": 0.15 | |
| } | |
| ], | |
| "max_steps": 508, | |
| "num_train_epochs": 4, | |
| "total_flos": 3.0193916980494336e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |