Instructions to use ahj224/tmp2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ahj224/tmp2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ahj224/tmp2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ahj224/tmp2") model = AutoModelForCausalLM.from_pretrained("ahj224/tmp2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ahj224/tmp2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ahj224/tmp2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ahj224/tmp2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ahj224/tmp2
- SGLang
How to use ahj224/tmp2 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 "ahj224/tmp2" \ --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": "ahj224/tmp2", "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 "ahj224/tmp2" \ --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": "ahj224/tmp2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ahj224/tmp2 with Docker Model Runner:
docker model run hf.co/ahj224/tmp2
Download trainer_state.json from ahj224/tmp2: direct link, hf CLI and curl.
- Browser
- Download file 713 Bytes
-
https://huggingface.co/ahj224/tmp2/resolve/main/trainer_state.json
- Command line
-
hf download hf://ahj224/tmp2/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/ahj224/tmp2/resolve/main/trainer_state.json
713 Bytes
| { | |
| "best_metric": 1.9337458610534668, | |
| "best_model_checkpoint": "./output/checkpoint-1", | |
| "epoch": 0.010749076251259657, | |
| "global_step": 1, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 1.9288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.9337458610534668, | |
| "eval_runtime": 146.9102, | |
| "eval_samples_per_second": 13.614, | |
| "eval_steps_per_second": 1.702, | |
| "step": 1 | |
| } | |
| ], | |
| "max_steps": 465, | |
| "num_train_epochs": 5, | |
| "total_flos": 5199528210726912.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |