Instructions to use Gege24/smoke_test_cm_2_ld with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Gege24/smoke_test_cm_2_ld with PEFT:
Base model is not found.
- Transformers
How to use Gege24/smoke_test_cm_2_ld with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Gege24/smoke_test_cm_2_ld") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Gege24/smoke_test_cm_2_ld", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Gege24/smoke_test_cm_2_ld with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gege24/smoke_test_cm_2_ld" # 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/smoke_test_cm_2_ld", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Gege24/smoke_test_cm_2_ld
- SGLang
How to use Gege24/smoke_test_cm_2_ld 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/smoke_test_cm_2_ld" \ --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/smoke_test_cm_2_ld", "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/smoke_test_cm_2_ld" \ --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/smoke_test_cm_2_ld", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Gege24/smoke_test_cm_2_ld with Docker Model Runner:
docker model run hf.co/Gege24/smoke_test_cm_2_ld
| { | |
| "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": 742.0, | |
| "completions/max_terminated_length": 742.0, | |
| "completions/mean_length": 398.875, | |
| "completions/mean_terminated_length": 395.6451416015625, | |
| "completions/min_length": 3.0, | |
| "completions/min_terminated_length": 3.0, | |
| "entropy": 3.4000556468963623, | |
| "epoch": 1e-05, | |
| "frac_reward_zero_std": 0.0, | |
| "grad_norm": 0.1924414336681366, | |
| "kl": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": -0.0124, | |
| "num_tokens": 51833.0, | |
| "reward": -0.6493932008743286, | |
| "reward_std": 2.6031136512756348, | |
| "rewards/rollout_reward_func/mean": -0.6493932008743286, | |
| "rewards/rollout_reward_func/std": 2.8167521953582764, | |
| "sampling/importance_sampling_ratio/max": 0.4791015088558197, | |
| "sampling/importance_sampling_ratio/mean": 0.17841634154319763, | |
| "sampling/importance_sampling_ratio/min": 0.0016821605386212468, | |
| "sampling/sampling_logp_difference/max": 2.841782569885254, | |
| "sampling/sampling_logp_difference/mean": 0.4031297564506531, | |
| "step": 1, | |
| "step_time": 9.75538970198977 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 400000, | |
| "num_input_tokens_seen": 51833, | |
| "num_train_epochs": 4, | |
| "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 | |
| } | |