Instructions to use socius/Smoltaur-0.4B-LoRA-r64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use socius/Smoltaur-0.4B-LoRA-r64 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/SmolLM2-360M") model = PeftModel.from_pretrained(base_model, "socius/Smoltaur-0.4B-LoRA-r64") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use socius/Smoltaur-0.4B-LoRA-r64 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 socius/Smoltaur-0.4B-LoRA-r64 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 socius/Smoltaur-0.4B-LoRA-r64 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for socius/Smoltaur-0.4B-LoRA-r64 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="socius/Smoltaur-0.4B-LoRA-r64", max_seq_length=2048, )
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.26625840378086935, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005325168075617386, | |
| "grad_norm": 1.179490566253662, | |
| "learning_rate": 4.787234042553191e-06, | |
| "loss": 0.7552515983581543, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010650336151234773, | |
| "grad_norm": 0.7021263837814331, | |
| "learning_rate": 1.0106382978723404e-05, | |
| "loss": 0.7758663654327392, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01597550422685216, | |
| "grad_norm": 0.6242384314537048, | |
| "learning_rate": 1.5425531914893617e-05, | |
| "loss": 0.620504903793335, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021300672302469546, | |
| "grad_norm": 0.4310513138771057, | |
| "learning_rate": 2.074468085106383e-05, | |
| "loss": 0.6261196613311768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026625840378086935, | |
| "grad_norm": 0.5022103786468506, | |
| "learning_rate": 2.6063829787234046e-05, | |
| "loss": 0.6593732833862305, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03195100845370432, | |
| "grad_norm": 0.6999115943908691, | |
| "learning_rate": 3.1382978723404254e-05, | |
| "loss": 0.687755012512207, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.037276176529321706, | |
| "grad_norm": 0.4458341598510742, | |
| "learning_rate": 3.670212765957447e-05, | |
| "loss": 0.6062395572662354, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04260134460493909, | |
| "grad_norm": 0.5636934638023376, | |
| "learning_rate": 4.2021276595744684e-05, | |
| "loss": 0.6789586544036865, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04792651268055648, | |
| "grad_norm": 0.47693607211112976, | |
| "learning_rate": 4.734042553191489e-05, | |
| "loss": 0.5777320384979248, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05325168075617387, | |
| "grad_norm": 0.5000275373458862, | |
| "learning_rate": 4.985986547085202e-05, | |
| "loss": 0.5979567527770996, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.058576848831791255, | |
| "grad_norm": 0.7978994250297546, | |
| "learning_rate": 4.9579596412556055e-05, | |
| "loss": 0.5918041229248047, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06390201690740864, | |
| "grad_norm": 0.6180557012557983, | |
| "learning_rate": 4.9299327354260097e-05, | |
| "loss": 0.6245941162109375, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06922718498302603, | |
| "grad_norm": 0.8771600723266602, | |
| "learning_rate": 4.9019058295964125e-05, | |
| "loss": 0.5516412258148193, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07455235305864341, | |
| "grad_norm": 0.570806622505188, | |
| "learning_rate": 4.8738789237668166e-05, | |
| "loss": 0.6044556140899658, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0798775211342608, | |
| "grad_norm": 0.5548396110534668, | |
| "learning_rate": 4.84585201793722e-05, | |
| "loss": 0.5861228466033935, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08520268920987818, | |
| "grad_norm": 0.3578498661518097, | |
| "learning_rate": 4.8178251121076236e-05, | |
| "loss": 0.5874335289001464, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09052785728549557, | |
| "grad_norm": 0.6209887266159058, | |
| "learning_rate": 4.789798206278027e-05, | |
| "loss": 0.5836649894714355, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09585302536111295, | |
| "grad_norm": 0.5073224902153015, | |
| "learning_rate": 4.7617713004484306e-05, | |
| "loss": 0.5651541233062745, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.10117819343673035, | |
| "grad_norm": 0.5013888478279114, | |
| "learning_rate": 4.733744394618834e-05, | |
| "loss": 0.5798611164093017, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10650336151234774, | |
| "grad_norm": 0.2958514094352722, | |
| "learning_rate": 4.705717488789238e-05, | |
| "loss": 0.5263164520263672, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11182852958796512, | |
| "grad_norm": 0.5098234415054321, | |
| "learning_rate": 4.677690582959641e-05, | |
| "loss": 0.6066572189331054, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11715369766358251, | |
| "grad_norm": 0.68392413854599, | |
| "learning_rate": 4.649663677130045e-05, | |
| "loss": 0.501525592803955, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.12247886573919989, | |
| "grad_norm": 0.5342642068862915, | |
| "learning_rate": 4.621636771300449e-05, | |
| "loss": 0.5538065910339356, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12780403381481728, | |
| "grad_norm": 0.46322742104530334, | |
| "learning_rate": 4.593609865470852e-05, | |
| "loss": 0.6028264999389649, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13312920189043467, | |
| "grad_norm": 0.5507689714431763, | |
| "learning_rate": 4.565582959641256e-05, | |
| "loss": 0.524617338180542, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13845436996605207, | |
| "grad_norm": 0.5451244711875916, | |
| "learning_rate": 4.537556053811659e-05, | |
| "loss": 0.5184399604797363, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14377953804166943, | |
| "grad_norm": 0.4679802656173706, | |
| "learning_rate": 4.509529147982063e-05, | |
| "loss": 0.5906213760375977, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.14910470611728682, | |
| "grad_norm": 0.4486578702926636, | |
| "learning_rate": 4.481502242152467e-05, | |
| "loss": 0.5088740348815918, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15442987419290422, | |
| "grad_norm": 0.3085339665412903, | |
| "learning_rate": 4.4534753363228704e-05, | |
| "loss": 0.5231688499450684, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1597550422685216, | |
| "grad_norm": 0.8423092365264893, | |
| "learning_rate": 4.425448430493274e-05, | |
| "loss": 0.5785892963409424, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.165080210344139, | |
| "grad_norm": 0.8173497319221497, | |
| "learning_rate": 4.3974215246636774e-05, | |
| "loss": 0.5546716690063477, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.17040537841975636, | |
| "grad_norm": 0.4842700958251953, | |
| "learning_rate": 4.369394618834081e-05, | |
| "loss": 0.5258895874023437, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17573054649537376, | |
| "grad_norm": 0.645687460899353, | |
| "learning_rate": 4.3413677130044844e-05, | |
| "loss": 0.5903552532196045, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.18105571457099115, | |
| "grad_norm": 0.5248221755027771, | |
| "learning_rate": 4.313340807174888e-05, | |
| "loss": 0.5313117027282714, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18638088264660854, | |
| "grad_norm": 0.4039202928543091, | |
| "learning_rate": 4.2853139013452914e-05, | |
| "loss": 0.5434175491333008, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1917060507222259, | |
| "grad_norm": 0.6575778126716614, | |
| "learning_rate": 4.257286995515695e-05, | |
| "loss": 0.5336236476898193, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1970312187978433, | |
| "grad_norm": 0.6030762791633606, | |
| "learning_rate": 4.229260089686099e-05, | |
| "loss": 0.5873087406158447, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2023563868734607, | |
| "grad_norm": 0.36645743250846863, | |
| "learning_rate": 4.201233183856502e-05, | |
| "loss": 0.44643635749816896, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.20768155494907808, | |
| "grad_norm": 0.38583752512931824, | |
| "learning_rate": 4.173206278026906e-05, | |
| "loss": 0.48238911628723147, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.21300672302469548, | |
| "grad_norm": 0.3569328486919403, | |
| "learning_rate": 4.1451793721973096e-05, | |
| "loss": 0.5249658107757569, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21833189110031284, | |
| "grad_norm": 0.5705183744430542, | |
| "learning_rate": 4.117152466367713e-05, | |
| "loss": 0.5840038299560547, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.22365705917593023, | |
| "grad_norm": 0.5844929218292236, | |
| "learning_rate": 4.0891255605381166e-05, | |
| "loss": 0.49370269775390624, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22898222725154763, | |
| "grad_norm": 0.4003148376941681, | |
| "learning_rate": 4.061098654708521e-05, | |
| "loss": 0.5035266876220703, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.23430739532716502, | |
| "grad_norm": 0.4637913405895233, | |
| "learning_rate": 4.0330717488789236e-05, | |
| "loss": 0.4923057556152344, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2396325634027824, | |
| "grad_norm": 0.41266828775405884, | |
| "learning_rate": 4.005044843049328e-05, | |
| "loss": 0.48969035148620604, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24495773147839978, | |
| "grad_norm": 0.6229465007781982, | |
| "learning_rate": 3.977017937219731e-05, | |
| "loss": 0.5537493228912354, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.25028289955401717, | |
| "grad_norm": 0.3518058657646179, | |
| "learning_rate": 3.948991031390135e-05, | |
| "loss": 0.5104994297027587, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.25560806762963456, | |
| "grad_norm": 0.3331281840801239, | |
| "learning_rate": 3.920964125560538e-05, | |
| "loss": 0.48421249389648435, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.26093323570525195, | |
| "grad_norm": 0.6162995100021362, | |
| "learning_rate": 3.8929372197309424e-05, | |
| "loss": 0.5097816944122314, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.26625840378086935, | |
| "grad_norm": 0.7575991153717041, | |
| "learning_rate": 3.864910313901345e-05, | |
| "loss": 0.538728666305542, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1878, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.087945270656128e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |