Instructions to use EclipseMist/Zexy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use EclipseMist/Zexy with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3.5-27B") model = PeftModel.from_pretrained(base_model, "EclipseMist/Zexy") - Transformers
How to use EclipseMist/Zexy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="EclipseMist/Zexy") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("EclipseMist/Zexy", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use EclipseMist/Zexy with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EclipseMist/Zexy" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EclipseMist/Zexy", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/EclipseMist/Zexy
- SGLang
How to use EclipseMist/Zexy 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 "EclipseMist/Zexy" \ --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": "EclipseMist/Zexy", "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 "EclipseMist/Zexy" \ --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": "EclipseMist/Zexy", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use EclipseMist/Zexy with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for EclipseMist/Zexy to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for EclipseMist/Zexy to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for EclipseMist/Zexy to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="EclipseMist/Zexy", max_seq_length=2048, ) - Docker Model Runner
How to use EclipseMist/Zexy with Docker Model Runner:
docker model run hf.co/EclipseMist/Zexy
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 217, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02304147465437788, | |
| "grad_norm": 4.609155178070068, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1945276260375977, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04608294930875576, | |
| "grad_norm": 0.3184139132499695, | |
| "learning_rate": 9e-05, | |
| "loss": 1.017074966430664, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06912442396313365, | |
| "grad_norm": 0.21383991837501526, | |
| "learning_rate": 0.00014, | |
| "loss": 0.956594181060791, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09216589861751152, | |
| "grad_norm": 0.20728200674057007, | |
| "learning_rate": 0.00019, | |
| "loss": 0.9034479141235352, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1152073732718894, | |
| "grad_norm": 0.1944284737110138, | |
| "learning_rate": 0.00019979661917102115, | |
| "loss": 0.8788949012756347, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1382488479262673, | |
| "grad_norm": 0.18074148893356323, | |
| "learning_rate": 0.00019897180218885507, | |
| "loss": 0.9575190544128418, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16129032258064516, | |
| "grad_norm": 0.29437240958213806, | |
| "learning_rate": 0.00019751807495903484, | |
| "loss": 0.9204333305358887, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18433179723502305, | |
| "grad_norm": 0.22639837861061096, | |
| "learning_rate": 0.00019544467510209388, | |
| "loss": 1.0152652740478516, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2073732718894009, | |
| "grad_norm": 0.21111330389976501, | |
| "learning_rate": 0.00019276477791027374, | |
| "loss": 0.8392349243164062, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2304147465437788, | |
| "grad_norm": 0.2804746925830841, | |
| "learning_rate": 0.00018949541262593762, | |
| "loss": 0.7984195232391358, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2534562211981567, | |
| "grad_norm": 0.18596959114074707, | |
| "learning_rate": 0.00018565735423029404, | |
| "loss": 0.8844935417175293, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2764976958525346, | |
| "grad_norm": 0.3064640462398529, | |
| "learning_rate": 0.00018127499143005268, | |
| "loss": 0.8820157051086426, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2995391705069124, | |
| "grad_norm": 0.23555733263492584, | |
| "learning_rate": 0.00017637617168088325, | |
| "loss": 0.9234310150146484, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 0.18329502642154694, | |
| "learning_rate": 0.0001709920242324663, | |
| "loss": 0.8056103706359863, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3456221198156682, | |
| "grad_norm": 0.1875191181898117, | |
| "learning_rate": 0.0001651567623195849, | |
| "loss": 0.979500675201416, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3686635944700461, | |
| "grad_norm": 0.22501425445079803, | |
| "learning_rate": 0.00015890746575622231, | |
| "loss": 0.8597883224487305, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.391705069124424, | |
| "grad_norm": 0.17843660712242126, | |
| "learning_rate": 0.0001522838453141581, | |
| "loss": 0.7388361930847168, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4147465437788018, | |
| "grad_norm": 0.24085059762001038, | |
| "learning_rate": 0.00014532799038330385, | |
| "loss": 1.0389366149902344, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4377880184331797, | |
| "grad_norm": 0.2150639444589615, | |
| "learning_rate": 0.0001380841015172563, | |
| "loss": 0.8493513107299805, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4608294930875576, | |
| "grad_norm": 0.18283779919147491, | |
| "learning_rate": 0.00013059820956358998, | |
| "loss": 1.0224772453308106, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "grad_norm": 0.23088669776916504, | |
| "learning_rate": 0.00012291788316365888, | |
| "loss": 0.7935346126556396, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5069124423963134, | |
| "grad_norm": 0.20359237492084503, | |
| "learning_rate": 0.00011509192648058249, | |
| "loss": 0.880291748046875, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5299539170506913, | |
| "grad_norm": 0.2222241908311844, | |
| "learning_rate": 0.00010717006907618377, | |
| "loss": 1.0091294288635253, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5529953917050692, | |
| "grad_norm": 0.23833954334259033, | |
| "learning_rate": 9.920264990753837e-05, | |
| "loss": 0.8710408210754395, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.576036866359447, | |
| "grad_norm": 0.21623441576957703, | |
| "learning_rate": 9.12402974511587e-05, | |
| "loss": 0.7930989265441895, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5990783410138248, | |
| "grad_norm": 0.131376251578331, | |
| "learning_rate": 8.333360798744496e-05, | |
| "loss": 0.7971048831939698, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6221198156682027, | |
| "grad_norm": 0.21020947396755219, | |
| "learning_rate": 7.553282408972382e-05, | |
| "loss": 0.9506874084472656, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.1900622397661209, | |
| "learning_rate": 6.788751536089739e-05, | |
| "loss": 0.7837625980377197, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6682027649769585, | |
| "grad_norm": 0.20265358686447144, | |
| "learning_rate": 6.044626344644151e-05, | |
| "loss": 0.9717947959899902, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6912442396313364, | |
| "grad_norm": 0.20827989280223846, | |
| "learning_rate": 5.325635332531864e-05, | |
| "loss": 0.8602096557617187, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.18106794357299805, | |
| "learning_rate": 4.636347284047877e-05, | |
| "loss": 0.7170271873474121, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7373271889400922, | |
| "grad_norm": 0.1832089126110077, | |
| "learning_rate": 3.981142237826332e-05, | |
| "loss": 0.927896785736084, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7603686635944701, | |
| "grad_norm": 0.2030986100435257, | |
| "learning_rate": 3.364183654153592e-05, | |
| "loss": 0.7584274768829345, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.783410138248848, | |
| "grad_norm": 0.22505062818527222, | |
| "learning_rate": 2.789391958515183e-05, | |
| "loss": 0.8892077445983887, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8064516129032258, | |
| "grad_norm": 0.22897103428840637, | |
| "learning_rate": 2.2604196294924694e-05, | |
| "loss": 0.7206392288208008, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.8294930875576036, | |
| "grad_norm": 0.16774588823318481, | |
| "learning_rate": 1.7806279893114875e-05, | |
| "loss": 0.854553508758545, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8525345622119815, | |
| "grad_norm": 0.21229791641235352, | |
| "learning_rate": 1.3530658445269783e-05, | |
| "loss": 0.9499557495117188, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8755760368663594, | |
| "grad_norm": 0.2512429356575012, | |
| "learning_rate": 9.804501125681243e-06, | |
| "loss": 0.8282492637634278, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8986175115207373, | |
| "grad_norm": 0.2164967805147171, | |
| "learning_rate": 6.651485572533378e-06, | |
| "loss": 0.8490478515625, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.9216589861751152, | |
| "grad_norm": 0.22630353271961212, | |
| "learning_rate": 4.091647429802869e-06, | |
| "loss": 0.8240178108215332, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9447004608294931, | |
| "grad_norm": 0.2094026803970337, | |
| "learning_rate": 2.1412530319879887e-06, | |
| "loss": 0.8646288871765136, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 0.22000199556350708, | |
| "learning_rate": 8.126960406835249e-07, | |
| "loss": 0.7955609798431397, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9907834101382489, | |
| "grad_norm": 0.2844116985797882, | |
| "learning_rate": 1.1441868981815207e-07, | |
| "loss": 0.9579826354980469, | |
| "step": 215 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 217, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.887535275770291e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |