Instructions to use thepikachu/architecture-sft-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use thepikachu/architecture-sft-model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "thepikachu/architecture-sft-model") - Transformers
How to use thepikachu/architecture-sft-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="thepikachu/architecture-sft-model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("thepikachu/architecture-sft-model", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use thepikachu/architecture-sft-model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "thepikachu/architecture-sft-model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thepikachu/architecture-sft-model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/thepikachu/architecture-sft-model
- SGLang
How to use thepikachu/architecture-sft-model 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 "thepikachu/architecture-sft-model" \ --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": "thepikachu/architecture-sft-model", "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 "thepikachu/architecture-sft-model" \ --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": "thepikachu/architecture-sft-model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use thepikachu/architecture-sft-model 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 thepikachu/architecture-sft-model 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 thepikachu/architecture-sft-model to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for thepikachu/architecture-sft-model to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="thepikachu/architecture-sft-model", max_seq_length=2048, ) - Docker Model Runner
How to use thepikachu/architecture-sft-model with Docker Model Runner:
docker model run hf.co/thepikachu/architecture-sft-model
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 2.234692335128784, | |
| "learning_rate": 0.00016, | |
| "loss": 3.564731216430664, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 1.4577325582504272, | |
| "learning_rate": 0.00019448275862068965, | |
| "loss": 1.7822282791137696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.2280287742614746, | |
| "learning_rate": 0.00018758620689655173, | |
| "loss": 0.5553516387939453, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.39766302704811096, | |
| "learning_rate": 0.00018068965517241382, | |
| "loss": 0.1261259436607361, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.36177533864974976, | |
| "learning_rate": 0.00017379310344827587, | |
| "loss": 0.0433908075094223, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.1993640512228012, | |
| "learning_rate": 0.00016689655172413793, | |
| "loss": 0.014871008694171906, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 0.1327141374349594, | |
| "learning_rate": 0.00016, | |
| "loss": 0.008725088089704514, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.05042891949415207, | |
| "learning_rate": 0.00015310344827586207, | |
| "loss": 0.007357730716466904, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.09038956463336945, | |
| "learning_rate": 0.00014620689655172415, | |
| "loss": 0.006654418259859085, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.07532325387001038, | |
| "learning_rate": 0.0001393103448275862, | |
| "loss": 0.00647946298122406, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.6666666666666665, | |
| "grad_norm": 0.08514901250600815, | |
| "learning_rate": 0.0001324137931034483, | |
| "loss": 0.006680632382631302, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.0902906134724617, | |
| "learning_rate": 0.00012551724137931035, | |
| "loss": 0.0068584330379962925, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.333333333333333, | |
| "grad_norm": 0.06367665529251099, | |
| "learning_rate": 0.0001186206896551724, | |
| "loss": 0.006411250680685043, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.0606352835893631, | |
| "learning_rate": 0.00011172413793103449, | |
| "loss": 0.006474435329437256, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.058691803365945816, | |
| "learning_rate": 0.00010482758620689656, | |
| "loss": 0.006187014281749725, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.06785333156585693, | |
| "learning_rate": 9.793103448275862e-05, | |
| "loss": 0.007109149545431137, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.666666666666667, | |
| "grad_norm": 0.041070930659770966, | |
| "learning_rate": 9.10344827586207e-05, | |
| "loss": 0.006115003302693367, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.046001601964235306, | |
| "learning_rate": 8.413793103448277e-05, | |
| "loss": 0.006253865361213684, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.333333333333333, | |
| "grad_norm": 0.04734743386507034, | |
| "learning_rate": 7.724137931034483e-05, | |
| "loss": 0.0060293667018413545, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.04042210429906845, | |
| "learning_rate": 7.03448275862069e-05, | |
| "loss": 0.0062621280550956724, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.04954440891742706, | |
| "learning_rate": 6.344827586206897e-05, | |
| "loss": 0.00619029626250267, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 7.333333333333333, | |
| "grad_norm": 0.058896154165267944, | |
| "learning_rate": 5.6551724137931037e-05, | |
| "loss": 0.005703266337513923, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 7.666666666666667, | |
| "grad_norm": 0.017007876187562943, | |
| "learning_rate": 4.9655172413793107e-05, | |
| "loss": 0.005966300517320633, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.017122946679592133, | |
| "learning_rate": 4.275862068965518e-05, | |
| "loss": 0.005790818855166436, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 0.066221684217453, | |
| "learning_rate": 3.586206896551724e-05, | |
| "loss": 0.005818406492471695, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 8.666666666666666, | |
| "grad_norm": 0.06780843436717987, | |
| "learning_rate": 2.8965517241379313e-05, | |
| "loss": 0.006129764020442963, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.038115620613098145, | |
| "learning_rate": 2.206896551724138e-05, | |
| "loss": 0.005897220596671105, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 9.333333333333334, | |
| "grad_norm": 0.07508810609579086, | |
| "learning_rate": 1.5172413793103448e-05, | |
| "loss": 0.005739358067512512, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 9.666666666666666, | |
| "grad_norm": 0.06934335082769394, | |
| "learning_rate": 8.275862068965518e-06, | |
| "loss": 0.006111703440546989, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.06771335750818253, | |
| "learning_rate": 1.3793103448275862e-06, | |
| "loss": 0.0057536657899618145, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6536089957171200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |