Instructions to use Gege24/test_train_A_liars_dice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Gege24/test_train_A_liars_dice with PEFT:
Base model is not found.
- Transformers
How to use Gege24/test_train_A_liars_dice with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Gege24/test_train_A_liars_dice") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Gege24/test_train_A_liars_dice", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Gege24/test_train_A_liars_dice with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gege24/test_train_A_liars_dice" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gege24/test_train_A_liars_dice", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Gege24/test_train_A_liars_dice
- SGLang
How to use Gege24/test_train_A_liars_dice 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 "Gege24/test_train_A_liars_dice" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gege24/test_train_A_liars_dice", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Gege24/test_train_A_liars_dice" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gege24/test_train_A_liars_dice", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Gege24/test_train_A_liars_dice with Docker Model Runner:
docker model run hf.co/Gege24/test_train_A_liars_dice
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1e-05, | |
| "eval_steps": 500, | |
| "global_step": 1, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "clip_ratio/high_max": 0.0, | |
| "clip_ratio/high_mean": 0.0, | |
| "clip_ratio/low_mean": 0.0, | |
| "clip_ratio/low_min": 0.0, | |
| "clip_ratio/region_mean": 0.0, | |
| "completions/clipped_ratio": 0.03125, | |
| "completions/max_length": 942.0, | |
| "completions/max_terminated_length": 942.0, | |
| "completions/mean_length": 390.375, | |
| "completions/mean_terminated_length": 389.32257080078125, | |
| "completions/min_length": 2.0, | |
| "completions/min_terminated_length": 2.0, | |
| "entropy": 8.502744436264038, | |
| "epoch": 1e-05, | |
| "frac_reward_zero_std": 0.0, | |
| "grad_norm": 0.007989775389432907, | |
| "kl": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0002, | |
| "num_tokens": 49300.0, | |
| "reward": 0.5077679753303528, | |
| "reward_std": 1.4316442012786865, | |
| "rewards/rollout_reward_func/mean": 0.5077679753303528, | |
| "rewards/rollout_reward_func/std": 1.383098840713501, | |
| "sampling/importance_sampling_ratio/max": 0.05534586310386658, | |
| "sampling/importance_sampling_ratio/mean": 0.0062338062562048435, | |
| "sampling/importance_sampling_ratio/min": 6.590540592920583e-15, | |
| "sampling/sampling_logp_difference/max": 4.380148410797119, | |
| "sampling/sampling_logp_difference/mean": 1.538283348083496, | |
| "step": 1, | |
| "step_time": 9.570080434999909 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 200000, | |
| "num_input_tokens_seen": 49300, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |