Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/onereason_0.8b_sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/onereason_0.8b_sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/onereason_0.8b_sft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/onereason_0.8b_sft") model = AutoModelForCausalLM.from_pretrained("lldois/onereason_0.8b_sft", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lldois/onereason_0.8b_sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/onereason_0.8b_sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lldois/onereason_0.8b_sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/onereason_0.8b_sft
- SGLang
How to use lldois/onereason_0.8b_sft 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 "lldois/onereason_0.8b_sft" \ --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": "lldois/onereason_0.8b_sft", "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 "lldois/onereason_0.8b_sft" \ --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": "lldois/onereason_0.8b_sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/onereason_0.8b_sft with Docker Model Runner:
docker model run hf.co/lldois/onereason_0.8b_sft
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012523481527864746, | |
| "grad_norm": 29.625, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 3.0092775344848635, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025046963055729492, | |
| "grad_norm": 8.8125, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 2.547764778137207, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03757044458359424, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.9998688836656322e-05, | |
| "loss": 2.233675956726074, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.050093926111458985, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 1.9983942197426272e-05, | |
| "loss": 2.057873344421387, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06261740763932373, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 1.995283421166614e-05, | |
| "loss": 1.851465606689453, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07514088916718847, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 1.9905415858090036e-05, | |
| "loss": 1.855565071105957, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08766437069505323, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 1.9841764844290744e-05, | |
| "loss": 1.752499771118164, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10018785222291797, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 1.976198547939518e-05, | |
| "loss": 1.8114988327026367, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11271133375078271, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.9666208503126115e-05, | |
| "loss": 1.6981731414794923, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12523481527864747, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.955459087155033e-05, | |
| "loss": 1.6682065963745116, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13775829680651222, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.9427315499864345e-05, | |
| "loss": 1.654319953918457, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15028177833437695, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.928459096263918e-05, | |
| "loss": 1.628897476196289, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1628052598622417, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.9126651152015404e-05, | |
| "loss": 1.588959312438965, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17532874139010646, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.8953754894408617e-05, | |
| "loss": 1.643252182006836, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18785222291797118, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.876618552635348e-05, | |
| "loss": 1.575343132019043, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20037570444583594, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.8564250430181387e-05, | |
| "loss": 1.6070398330688476, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2128991859737007, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.8348280530292712e-05, | |
| "loss": 1.6005193710327148, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22542266750156542, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.8118629750849106e-05, | |
| "loss": 1.5561012268066405, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23794614902943018, | |
| "grad_norm": 1.9140625, | |
| "learning_rate": 1.7875674435774546e-05, | |
| "loss": 1.5994838714599608, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25046963055729493, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.7619812732015664e-05, | |
| "loss": 1.5856236457824706, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2629931120851597, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.7351463937072008e-05, | |
| "loss": 1.5562751770019532, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.27551659361302444, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 1.5253159523010253, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28804007514088914, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.6779083860075032e-05, | |
| "loss": 1.5002705574035644, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3005635566687539, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.6475990575117603e-05, | |
| "loss": 1.5255040168762206, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31308703819661865, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 1.6162284656009276e-05, | |
| "loss": 1.489553737640381, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3256105197244834, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.5838480193391753e-05, | |
| "loss": 1.4954115867614746, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33813400125234816, | |
| "grad_norm": 1.921875, | |
| "learning_rate": 1.5505107827058038e-05, | |
| "loss": 1.504003143310547, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3506574827802129, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 1.516271387635786e-05, | |
| "loss": 1.5397921562194825, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.36318096430807767, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.4811859444908053e-05, | |
| "loss": 1.5844552040100097, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.37570444583594237, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.4453119501074924e-05, | |
| "loss": 1.4908522605895995, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3882279273638071, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.4087081935735565e-05, | |
| "loss": 1.4880791664123536, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.4007514088916719, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.3714346598862168e-05, | |
| "loss": 1.4971721649169922, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.41327489041953663, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 1.3335524316508208e-05, | |
| "loss": 1.4654574394226074, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4257983719474014, | |
| "grad_norm": 1.9296875, | |
| "learning_rate": 1.2951235889807386e-05, | |
| "loss": 1.450455379486084, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43832185347526614, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.2562111077625723e-05, | |
| "loss": 1.570608425140381, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.45084533500313084, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 1.2168787564534078e-05, | |
| "loss": 1.4704577445983886, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4633688165309956, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.177190991579223e-05, | |
| "loss": 1.5063845634460449, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.47589229805886035, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.1372128521057155e-05, | |
| "loss": 1.4744919776916503, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4884157795867251, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.0970098528546482e-05, | |
| "loss": 1.511544895172119, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5009392611145899, | |
| "grad_norm": 1.7578125, | |
| "learning_rate": 1.0566478771403763e-05, | |
| "loss": 1.4689907073974608, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5134627426424546, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.0161930688025018e-05, | |
| "loss": 1.4732332229614258, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5259862241703194, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 9.757117238115871e-06, | |
| "loss": 1.4493576049804688, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5385097056981841, | |
| "grad_norm": 1.9296875, | |
| "learning_rate": 9.352701816255643e-06, | |
| "loss": 1.4741571426391602, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5510331872260489, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 8.949347164748761e-06, | |
| "loss": 1.4440049171447753, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5635566687539136, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 8.5477142875451e-06, | |
| "loss": 1.5042129516601563, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5760801502817783, | |
| "grad_norm": 1.9921875, | |
| "learning_rate": 8.148461367009081e-06, | |
| "loss": 1.479151153564453, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.588603631809643, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 7.752242685312709e-06, | |
| "loss": 1.5147887229919434, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6011271133375078, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 7.35970755222007e-06, | |
| "loss": 1.4407625198364258, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6136505948653725, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 6.971499241020495e-06, | |
| "loss": 1.4036590576171875, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6261740763932373, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 6.588253934354039e-06, | |
| "loss": 1.4591806411743165, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.638697557921102, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 6.210599681656933e-06, | |
| "loss": 1.5027113914489747, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6512210394489668, | |
| "grad_norm": 1.953125, | |
| "learning_rate": 5.839155369935407e-06, | |
| "loss": 1.4685559272766113, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6637445209768316, | |
| "grad_norm": 2.375, | |
| "learning_rate": 5.4745297095546125e-06, | |
| "loss": 1.5166523933410645, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6762680025046963, | |
| "grad_norm": 2.625, | |
| "learning_rate": 5.117320236704697e-06, | |
| "loss": 1.4691507339477539, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6887914840325611, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 4.7681123341787e-06, | |
| "loss": 1.53342924118042, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7013149655604258, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 4.427478272067066e-06, | |
| "loss": 1.514073371887207, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7138384470882906, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 4.095976269940777e-06, | |
| "loss": 1.4454584121704102, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7263619286161553, | |
| "grad_norm": 1.828125, | |
| "learning_rate": 3.7741495820600128e-06, | |
| "loss": 1.4844335556030273, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.73888541014402, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 3.4625256071074776e-06, | |
| "loss": 1.4866701126098634, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7514088916718847, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 3.1616150239052647e-06, | |
| "loss": 1.4392054557800293, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7639323731997495, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 2.8719109545317102e-06, | |
| "loss": 1.4637357711791992, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7764558547276142, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 2.593888156209603e-06, | |
| "loss": 1.4387860298156738, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.788979336255479, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 2.328002243290138e-06, | |
| "loss": 1.4650882720947265, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8015028177833438, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 2.074688940607529e-06, | |
| "loss": 1.5315435409545899, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8140262993112085, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.8343633694278895e-06, | |
| "loss": 1.5125369071960448, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8265497808390733, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.607419367162577e-06, | |
| "loss": 1.4377523422241212, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.839073262366938, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.3942288419607476e-06, | |
| "loss": 1.4360872268676759, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8515967438948028, | |
| "grad_norm": 1.9609375, | |
| "learning_rate": 1.195141163238892e-06, | |
| "loss": 1.4957749366760253, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8641202254226675, | |
| "grad_norm": 1.7578125, | |
| "learning_rate": 1.010482589146048e-06, | |
| "loss": 1.4363853454589843, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8766437069505323, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 8.405557319029911e-07, | |
| "loss": 1.5025806427001953, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.889167188478397, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 6.856390618915775e-07, | |
| "loss": 1.4651078224182128, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.9016906700062617, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 5.459864513068991e-07, | |
| "loss": 1.464914894104004, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9142141515341264, | |
| "grad_norm": 1.890625, | |
| "learning_rate": 4.218267581201296e-07, | |
| "loss": 1.44300537109375, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9267376330619912, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 3.133634510338235e-07, | |
| "loss": 1.4994802474975586, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.939261114589856, | |
| "grad_norm": 2.25, | |
| "learning_rate": 2.2077427604429435e-07, | |
| "loss": 1.4373616218566894, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9517845961177207, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 1.4421096515749855e-07, | |
| "loss": 1.4988561630249024, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9643080776455855, | |
| "grad_norm": 2.25, | |
| "learning_rate": 8.379898773574924e-08, | |
| "loss": 1.5371465682983398, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.9768315591734502, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 3.963734488278248e-08, | |
| "loss": 1.4375405311584473, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.989355040701315, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.179840720409331e-08, | |
| "loss": 1.4510549545288085, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 3.277962084369257e-10, | |
| "loss": 1.4790672302246093, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 400, | |
| "total_flos": 1.9165347193492685e+17, | |
| "train_loss": 1.5697158980369568, | |
| "train_runtime": 3253.1715, | |
| "train_samples_per_second": 0.491, | |
| "train_steps_per_second": 0.123 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 400, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9165347193492685e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |