Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v06_no_think_input_lr2e5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v06_no_think_input_lr2e5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v06_no_think_input_lr2e5") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/v06_no_think_input_lr2e5") model = AutoModelForCausalLM.from_pretrained("lldois/v06_no_think_input_lr2e5", 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/v06_no_think_input_lr2e5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/v06_no_think_input_lr2e5" # 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/v06_no_think_input_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v06_no_think_input_lr2e5
- SGLang
How to use lldois/v06_no_think_input_lr2e5 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/v06_no_think_input_lr2e5" \ --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/v06_no_think_input_lr2e5", "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/v06_no_think_input_lr2e5" \ --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/v06_no_think_input_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v06_no_think_input_lr2e5 with Docker Model Runner:
docker model run hf.co/lldois/v06_no_think_input_lr2e5
| { | |
| "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": 30.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.8921972274780274, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025046963055729492, | |
| "grad_norm": 7.75, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 2.628790283203125, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03757044458359424, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.9998688836656322e-05, | |
| "loss": 2.347702980041504, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.050093926111458985, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.9983942197426272e-05, | |
| "loss": 2.0862865447998047, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06261740763932373, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.995283421166614e-05, | |
| "loss": 1.9360042572021485, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07514088916718847, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.9905415858090036e-05, | |
| "loss": 1.79677734375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08766437069505323, | |
| "grad_norm": 3.0, | |
| "learning_rate": 1.9841764844290744e-05, | |
| "loss": 1.8103729248046876, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10018785222291797, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.976198547939518e-05, | |
| "loss": 1.7013376235961915, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11271133375078271, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.9666208503126115e-05, | |
| "loss": 1.683538818359375, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12523481527864747, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.955459087155033e-05, | |
| "loss": 1.6649005889892579, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13775829680651222, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.9427315499864345e-05, | |
| "loss": 1.6299520492553712, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15028177833437695, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 1.928459096263918e-05, | |
| "loss": 1.6017047882080078, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1628052598622417, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.9126651152015404e-05, | |
| "loss": 1.7135601043701172, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17532874139010646, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.8953754894408617e-05, | |
| "loss": 1.5896422386169433, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18785222291797118, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.876618552635348e-05, | |
| "loss": 1.562188720703125, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20037570444583594, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.8564250430181387e-05, | |
| "loss": 1.5557002067565917, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2128991859737007, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.8348280530292712e-05, | |
| "loss": 1.539021873474121, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22542266750156542, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.8118629750849106e-05, | |
| "loss": 1.5848278999328613, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23794614902943018, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.7875674435774546e-05, | |
| "loss": 1.5281625747680665, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25046963055729493, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 1.7619812732015664e-05, | |
| "loss": 1.5766194343566895, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2629931120851597, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.7351463937072008e-05, | |
| "loss": 1.5553075790405273, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.27551659361302444, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 1.5199402809143066, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28804007514088914, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.6779083860075032e-05, | |
| "loss": 1.5134542465209961, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3005635566687539, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.6475990575117603e-05, | |
| "loss": 1.505027961730957, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31308703819661865, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.6162284656009276e-05, | |
| "loss": 1.5308698654174804, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3256105197244834, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.5838480193391753e-05, | |
| "loss": 1.5138086318969726, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33813400125234816, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 1.5505107827058038e-05, | |
| "loss": 1.4948357582092284, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3506574827802129, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 1.516271387635786e-05, | |
| "loss": 1.496281051635742, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.36318096430807767, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.4811859444908053e-05, | |
| "loss": 1.5079349517822265, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.37570444583594237, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.4453119501074924e-05, | |
| "loss": 1.5319823265075683, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3882279273638071, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.4087081935735565e-05, | |
| "loss": 1.5125651359558105, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.4007514088916719, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.3714346598862168e-05, | |
| "loss": 1.446236801147461, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.41327489041953663, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 1.3335524316508208e-05, | |
| "loss": 1.5198042869567872, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4257983719474014, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 1.2951235889807386e-05, | |
| "loss": 1.4537819862365722, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43832185347526614, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.2562111077625723e-05, | |
| "loss": 1.465320873260498, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.45084533500313084, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.2168787564534078e-05, | |
| "loss": 1.516792106628418, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4633688165309956, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.177190991579223e-05, | |
| "loss": 1.4903325080871581, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.47589229805886035, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.1372128521057155e-05, | |
| "loss": 1.4676374435424804, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4884157795867251, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 1.0970098528546482e-05, | |
| "loss": 1.4557581901550294, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5009392611145899, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.0566478771403763e-05, | |
| "loss": 1.4857282638549805, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5134627426424546, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 1.0161930688025018e-05, | |
| "loss": 1.4773930549621581, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5259862241703194, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 9.757117238115871e-06, | |
| "loss": 1.47579984664917, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5385097056981841, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 9.352701816255643e-06, | |
| "loss": 1.44418306350708, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5510331872260489, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 8.949347164748761e-06, | |
| "loss": 1.500422191619873, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5635566687539136, | |
| "grad_norm": 2.0, | |
| "learning_rate": 8.5477142875451e-06, | |
| "loss": 1.5320363998413087, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5760801502817783, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 8.148461367009081e-06, | |
| "loss": 1.4355751037597657, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.588603631809643, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 7.752242685312709e-06, | |
| "loss": 1.4459010124206544, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6011271133375078, | |
| "grad_norm": 1.84375, | |
| "learning_rate": 7.35970755222007e-06, | |
| "loss": 1.461744785308838, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6136505948653725, | |
| "grad_norm": 3.0, | |
| "learning_rate": 6.971499241020495e-06, | |
| "loss": 1.4327082633972168, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6261740763932373, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 6.588253934354039e-06, | |
| "loss": 1.4809480667114259, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.638697557921102, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 6.210599681656933e-06, | |
| "loss": 1.4388222694396973, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6512210394489668, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 5.839155369935407e-06, | |
| "loss": 1.4551708221435546, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6637445209768316, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 5.4745297095546125e-06, | |
| "loss": 1.530555248260498, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6762680025046963, | |
| "grad_norm": 1.8671875, | |
| "learning_rate": 5.117320236704697e-06, | |
| "loss": 1.4364937782287597, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6887914840325611, | |
| "grad_norm": 2.25, | |
| "learning_rate": 4.7681123341787e-06, | |
| "loss": 1.453016185760498, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7013149655604258, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 4.427478272067066e-06, | |
| "loss": 1.4480918884277343, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7138384470882906, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 4.095976269940777e-06, | |
| "loss": 1.4924870491027833, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7263619286161553, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 3.7741495820600128e-06, | |
| "loss": 1.456740951538086, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.73888541014402, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 3.4625256071074776e-06, | |
| "loss": 1.4691086769104005, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7514088916718847, | |
| "grad_norm": 1.953125, | |
| "learning_rate": 3.1616150239052647e-06, | |
| "loss": 1.4497017860412598, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7639323731997495, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 2.8719109545317102e-06, | |
| "loss": 1.5338096618652344, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7764558547276142, | |
| "grad_norm": 2.375, | |
| "learning_rate": 2.593888156209603e-06, | |
| "loss": 1.5372199058532714, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.788979336255479, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 2.328002243290138e-06, | |
| "loss": 1.4532548904418945, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8015028177833438, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 2.074688940607529e-06, | |
| "loss": 1.5102259635925293, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8140262993112085, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.8343633694278895e-06, | |
| "loss": 1.5231080055236816, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8265497808390733, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.607419367162577e-06, | |
| "loss": 1.4568578720092773, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.839073262366938, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 1.3942288419607476e-06, | |
| "loss": 1.4671332359313964, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8515967438948028, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 1.195141163238892e-06, | |
| "loss": 1.4900860786437988, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8641202254226675, | |
| "grad_norm": 1.8203125, | |
| "learning_rate": 1.010482589146048e-06, | |
| "loss": 1.4515322685241698, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8766437069505323, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 8.405557319029911e-07, | |
| "loss": 1.4923242568969726, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.889167188478397, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 6.856390618915775e-07, | |
| "loss": 1.425497817993164, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.9016906700062617, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 5.459864513068991e-07, | |
| "loss": 1.4502497673034669, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9142141515341264, | |
| "grad_norm": 2.125, | |
| "learning_rate": 4.218267581201296e-07, | |
| "loss": 1.4536723136901855, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9267376330619912, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 3.133634510338235e-07, | |
| "loss": 1.4516624450683593, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.939261114589856, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 2.2077427604429435e-07, | |
| "loss": 1.5296987533569335, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9517845961177207, | |
| "grad_norm": 2.25, | |
| "learning_rate": 1.4421096515749855e-07, | |
| "loss": 1.4879746437072754, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9643080776455855, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 8.379898773574924e-08, | |
| "loss": 1.5177797317504882, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.9768315591734502, | |
| "grad_norm": 2.125, | |
| "learning_rate": 3.963734488278248e-08, | |
| "loss": 1.5221965789794922, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.989355040701315, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 1.179840720409331e-08, | |
| "loss": 1.5340576171875, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.0, | |
| "learning_rate": 3.277962084369257e-10, | |
| "loss": 1.4072744369506835, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 400, | |
| "total_flos": 1.913639661702574e+17, | |
| "train_loss": 1.5678150677680969, | |
| "train_runtime": 3206.5361, | |
| "train_samples_per_second": 0.498, | |
| "train_steps_per_second": 0.125 | |
| } | |
| ], | |
| "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": 1.913639661702574e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |