Instructions to use naivecat/cherry_full_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use naivecat/cherry_full_7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="naivecat/cherry_full_7b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("naivecat/cherry_full_7b") model = AutoModelForCausalLM.from_pretrained("naivecat/cherry_full_7b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use naivecat/cherry_full_7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "naivecat/cherry_full_7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "naivecat/cherry_full_7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/naivecat/cherry_full_7b
- SGLang
How to use naivecat/cherry_full_7b 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 "naivecat/cherry_full_7b" \ --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": "naivecat/cherry_full_7b", "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 "naivecat/cherry_full_7b" \ --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": "naivecat/cherry_full_7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use naivecat/cherry_full_7b with Docker Model Runner:
docker model run hf.co/naivecat/cherry_full_7b
Download trainer_state.json from naivecat/cherry_full_7b: direct link, hf CLI and curl.
- Browser
- Download file 1.36 kB
-
https://huggingface.co/naivecat/cherry_full_7b/resolve/main/trainer_state.json
- Command line
-
hf download hf://naivecat/cherry_full_7b/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/naivecat/cherry_full_7b/resolve/main/trainer_state.json
1.36 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.896, | |
| "global_step": 7, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5398, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 1.6118, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.3033, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1445, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 1.1898, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 1.1864, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0, | |
| "loss": 1.0916, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "step": 7, | |
| "total_flos": 3035606045163520.0, | |
| "train_loss": 1.2953110592705863, | |
| "train_runtime": 682.8066, | |
| "train_samples_per_second": 1.465, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "max_steps": 7, | |
| "num_train_epochs": 1, | |
| "total_flos": 3035606045163520.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |