Instructions to use naivecat/cherry_5_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use naivecat/cherry_5_7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="naivecat/cherry_5_7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("naivecat/cherry_5_7B") model = AutoModelForCausalLM.from_pretrained("naivecat/cherry_5_7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use naivecat/cherry_5_7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "naivecat/cherry_5_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_5_7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/naivecat/cherry_5_7B
- SGLang
How to use naivecat/cherry_5_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_5_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_5_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_5_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_5_7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use naivecat/cherry_5_7B with Docker Model Runner:
docker model run hf.co/naivecat/cherry_5_7B
Download trainer_state.json from naivecat/cherry_5_7B: direct link, hf CLI and curl.
- Browser
- Download file 9.15 kB
-
https://huggingface.co/naivecat/cherry_5_7B/resolve/main/trainer_state.json
- Command line
-
hf download hf://naivecat/cherry_5_7B/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/naivecat/cherry_5_7B/resolve/main/trainer_state.json
9.15 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.961439588688946, | |
| "global_step": 72, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.6215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.6348, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4299, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9989636736467278e-05, | |
| "loss": 1.4334, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9958568425315316e-05, | |
| "loss": 1.468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.9906859460363307e-05, | |
| "loss": 1.4159, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.9834617016337424e-05, | |
| "loss": 1.4128, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.9741990826734793e-05, | |
| "loss": 1.3951, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.9629172873477995e-05, | |
| "loss": 1.3818, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.9496396989003195e-05, | |
| "loss": 1.342, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.9343938371606714e-05, | |
| "loss": 1.2873, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.917211301505453e-05, | |
| "loss": 1.3423, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.8981277053636963e-05, | |
| "loss": 1.4581, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.8771826024025944e-05, | |
| "loss": 1.3193, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8544194045464888e-05, | |
| "loss": 1.3919, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.8298852919990254e-05, | |
| "loss": 1.374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.8036311154549783e-05, | |
| "loss": 1.3812, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.77571129070442e-05, | |
| "loss": 1.3577, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.7461836858476858e-05, | |
| "loss": 1.3745, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.7151095013548996e-05, | |
| "loss": 1.3124, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.6825531432186545e-05, | |
| "loss": 1.3827, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.648582089462756e-05, | |
| "loss": 1.394, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.6132667502837164e-05, | |
| "loss": 1.3605, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.5766803221148676e-05, | |
| "loss": 1.35, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.538898635915576e-05, | |
| "loss": 1.1304, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.0308, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.4600650377311523e-05, | |
| "loss": 1.0333, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.4191765204166643e-05, | |
| "loss": 0.9938, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.3774191957526144e-05, | |
| "loss": 0.9677, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.3348796121709862e-05, | |
| "loss": 1.0101, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.291645939454825e-05, | |
| "loss": 0.9679, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.2478077859929e-05, | |
| "loss": 0.9704, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.2034560130526341e-05, | |
| "loss": 0.9165, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.1586825464562515e-05, | |
| "loss": 0.9524, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.113580186050475e-05, | |
| "loss": 0.9744, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.0682424133646712e-05, | |
| "loss": 0.9251, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.0227631978561057e-05, | |
| "loss": 0.92, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.772368021438943e-06, | |
| "loss": 0.947, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.317575866353293e-06, | |
| "loss": 0.9406, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.86419813949525e-06, | |
| "loss": 0.9803, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.413174535437486e-06, | |
| "loss": 0.932, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 7.965439869473664e-06, | |
| "loss": 0.9271, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 7.521922140071003e-06, | |
| "loss": 0.9081, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.0835406054517505e-06, | |
| "loss": 0.922, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 6.651203878290139e-06, | |
| "loss": 0.941, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 6.225808042473857e-06, | |
| "loss": 0.9436, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 5.8082347958333625e-06, | |
| "loss": 0.9453, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.399349622688479e-06, | |
| "loss": 0.9162, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.8596, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.611013640844245e-06, | |
| "loss": 0.8061, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.2331967788513295e-06, | |
| "loss": 0.7507, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.867332497162836e-06, | |
| "loss": 0.7905, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.5141791053724405e-06, | |
| "loss": 0.7714, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.174468567813461e-06, | |
| "loss": 0.7438, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.8489049864510053e-06, | |
| "loss": 0.6632, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.5381631415231455e-06, | |
| "loss": 0.7124, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.2428870929558012e-06, | |
| "loss": 0.7325, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.963688845450218e-06, | |
| "loss": 0.6903, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.7011470800097496e-06, | |
| "loss": 0.7075, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1.4558059545351144e-06, | |
| "loss": 0.6924, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.2281739759740575e-06, | |
| "loss": 0.7008, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.01872294636304e-06, | |
| "loss": 0.6721, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 8.278869849454718e-07, | |
| "loss": 0.6658, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.560616283932897e-07, | |
| "loss": 0.6464, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.036030109968082e-07, | |
| "loss": 0.7287, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.708271265220087e-07, | |
| "loss": 0.7194, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.5800917326521013e-07, | |
| "loss": 0.7061, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.6538298366257975e-07, | |
| "loss": 0.7292, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 9.314053963669245e-08, | |
| "loss": 0.7474, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.143157468468717e-08, | |
| "loss": 0.7519, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.0363263532724433e-08, | |
| "loss": 0.7462, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0, | |
| "loss": 0.6997, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "step": 72, | |
| "total_flos": 4.919620776283341e+16, | |
| "train_loss": 1.029880191716883, | |
| "train_runtime": 10310.4521, | |
| "train_samples_per_second": 0.905, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "max_steps": 72, | |
| "num_train_epochs": 3, | |
| "total_flos": 4.919620776283341e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |