Instructions to use 1010happy/AmongUsDistilled3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use 1010happy/AmongUsDistilled3B-Instruct with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "1010happy/AmongUsDistilled3B-Instruct") - Transformers
How to use 1010happy/AmongUsDistilled3B-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="1010happy/AmongUsDistilled3B-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("1010happy/AmongUsDistilled3B-Instruct", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use 1010happy/AmongUsDistilled3B-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "1010happy/AmongUsDistilled3B-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "1010happy/AmongUsDistilled3B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/1010happy/AmongUsDistilled3B-Instruct
- SGLang
How to use 1010happy/AmongUsDistilled3B-Instruct 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 "1010happy/AmongUsDistilled3B-Instruct" \ --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": "1010happy/AmongUsDistilled3B-Instruct", "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 "1010happy/AmongUsDistilled3B-Instruct" \ --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": "1010happy/AmongUsDistilled3B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use 1010happy/AmongUsDistilled3B-Instruct with Docker Model Runner:
docker model run hf.co/1010happy/AmongUsDistilled3B-Instruct
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 309, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09744214372716199, | |
| "grad_norm": 0.10498138517141342, | |
| "learning_rate": 2.9032258064516133e-05, | |
| "loss": 1.6591840744018556, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19488428745432398, | |
| "grad_norm": 0.06061352789402008, | |
| "learning_rate": 6.129032258064517e-05, | |
| "loss": 1.513698673248291, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.292326431181486, | |
| "grad_norm": 0.06488917768001556, | |
| "learning_rate": 9.35483870967742e-05, | |
| "loss": 1.4184258460998536, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.38976857490864797, | |
| "grad_norm": 0.0749744325876236, | |
| "learning_rate": 9.979581007037776e-05, | |
| "loss": 1.3041383743286132, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.48721071863581, | |
| "grad_norm": 0.07460002601146698, | |
| "learning_rate": 9.896914594073703e-05, | |
| "loss": 1.2645663261413573, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.584652862362972, | |
| "grad_norm": 0.07611106336116791, | |
| "learning_rate": 9.751778332739033e-05, | |
| "loss": 1.2547479629516602, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.682095006090134, | |
| "grad_norm": 0.07656759023666382, | |
| "learning_rate": 9.546023723619386e-05, | |
| "loss": 1.1752987861633302, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7795371498172959, | |
| "grad_norm": 0.09050241112709045, | |
| "learning_rate": 9.282275574435281e-05, | |
| "loss": 1.2098669052124023, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.876979293544458, | |
| "grad_norm": 0.09291807562112808, | |
| "learning_rate": 8.963898515418884e-05, | |
| "loss": 1.1355886459350586, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.97442143727162, | |
| "grad_norm": 0.09804459661245346, | |
| "learning_rate": 8.594954076788736e-05, | |
| "loss": 1.0925632476806642, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0682095006090133, | |
| "grad_norm": 0.0993494838476181, | |
| "learning_rate": 8.18014887588431e-05, | |
| "loss": 1.0427302360534667, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1656516443361755, | |
| "grad_norm": 0.10639823228120804, | |
| "learning_rate": 7.724774574936188e-05, | |
| "loss": 1.0110761642456054, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2630937880633373, | |
| "grad_norm": 0.11075429618358612, | |
| "learning_rate": 7.234640375429427e-05, | |
| "loss": 1.0307095527648926, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3605359317904995, | |
| "grad_norm": 0.13242679834365845, | |
| "learning_rate": 6.715998910228296e-05, | |
| "loss": 1.0275198936462402, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4579780755176615, | |
| "grad_norm": 0.12440798431634903, | |
| "learning_rate": 6.17546647885516e-05, | |
| "loss": 0.9846453666687012, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5554202192448234, | |
| "grad_norm": 0.1317114233970642, | |
| "learning_rate": 5.619938643480561e-05, | |
| "loss": 0.9936046600341797, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6528623629719854, | |
| "grad_norm": 0.13666915893554688, | |
| "learning_rate": 5.0565022623648995e-05, | |
| "loss": 1.0225310325622559, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7503045066991474, | |
| "grad_norm": 0.12991490960121155, | |
| "learning_rate": 4.4923450829394605e-05, | |
| "loss": 1.0015269279479981, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8477466504263094, | |
| "grad_norm": 0.13253197073936462, | |
| "learning_rate": 3.934664047846156e-05, | |
| "loss": 0.9895278930664062, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.9451887941534713, | |
| "grad_norm": 0.11419489234685898, | |
| "learning_rate": 3.390573483674142e-05, | |
| "loss": 0.9593095779418945, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.038976857490865, | |
| "grad_norm": 0.12307924777269363, | |
| "learning_rate": 2.8670143436278756e-05, | |
| "loss": 0.8937208175659179, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.1364190012180266, | |
| "grad_norm": 0.15227432548999786, | |
| "learning_rate": 2.3706656619162278e-05, | |
| "loss": 0.8942792892456055, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.233861144945189, | |
| "grad_norm": 0.13321051001548767, | |
| "learning_rate": 1.907859349437336e-05, | |
| "loss": 0.8793990135192871, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.331303288672351, | |
| "grad_norm": 0.13967254757881165, | |
| "learning_rate": 1.484499417709087e-05, | |
| "loss": 0.856902027130127, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.428745432399513, | |
| "grad_norm": 0.14552684128284454, | |
| "learning_rate": 1.1059866615040204e-05, | |
| "loss": 0.9242639541625977, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.5261875761266745, | |
| "grad_norm": 0.13452662527561188, | |
| "learning_rate": 7.77149761010898e-06, | |
| "loss": 0.8745415687561036, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.6236297198538368, | |
| "grad_norm": 0.14857880771160126, | |
| "learning_rate": 5.021836824513759e-06, | |
| "loss": 0.8519741058349609, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.721071863580999, | |
| "grad_norm": 0.14847053587436676, | |
| "learning_rate": 2.8459616297395466e-06, | |
| "loss": 0.8284287452697754, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.8185140073081607, | |
| "grad_norm": 0.13416051864624023, | |
| "learning_rate": 1.2716296251644e-06, | |
| "loss": 0.8645434379577637, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.915956151035323, | |
| "grad_norm": 0.1331121027469635, | |
| "learning_rate": 3.1892453488058803e-07, | |
| "loss": 0.9010993003845215, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 309, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.317731244054938e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |