Instructions to use mllm-dev/gen_test_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mllm-dev/gen_test_2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mllm-dev/gen_test_2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mllm-dev/gen_test_2") model = AutoModelForCausalLM.from_pretrained("mllm-dev/gen_test_2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mllm-dev/gen_test_2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mllm-dev/gen_test_2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mllm-dev/gen_test_2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mllm-dev/gen_test_2
- SGLang
How to use mllm-dev/gen_test_2 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 "mllm-dev/gen_test_2" \ --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": "mllm-dev/gen_test_2", "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 "mllm-dev/gen_test_2" \ --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": "mllm-dev/gen_test_2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mllm-dev/gen_test_2 with Docker Model Runner:
docker model run hf.co/mllm-dev/gen_test_2
| { | |
| "best_metric": 4.551311016082764, | |
| "best_model_checkpoint": "gen_test/checkpoint-2", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 4.76393461227417, | |
| "eval_runtime": 0.5527, | |
| "eval_samples_per_second": 180.921, | |
| "eval_steps_per_second": 1.809, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 4.551311016082764, | |
| "eval_runtime": 0.5172, | |
| "eval_samples_per_second": 193.34, | |
| "eval_steps_per_second": 1.933, | |
| "step": 2 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 104516812800000.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |