Instructions to use Ksjsjjdj/Gemmax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Ksjsjjdj/Gemmax with PEFT:
Task type is invalid.
- Transformers
How to use Ksjsjjdj/Gemmax with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ksjsjjdj/Gemmax")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Ksjsjjdj/Gemmax", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ksjsjjdj/Gemmax with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ksjsjjdj/Gemmax" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ksjsjjdj/Gemmax", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ksjsjjdj/Gemmax
- SGLang
How to use Ksjsjjdj/Gemmax 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 "Ksjsjjdj/Gemmax" \ --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": "Ksjsjjdj/Gemmax", "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 "Ksjsjjdj/Gemmax" \ --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": "Ksjsjjdj/Gemmax", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Ksjsjjdj/Gemmax with Docker Model Runner:
docker model run hf.co/Ksjsjjdj/Gemmax
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 7.938793182373047, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 26.208885192871094, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 2.4883, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 9.038559913635254, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.2042, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1892242763520.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |