Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v01_all_lr1e5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v01_all_lr1e5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v01_all_lr1e5") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/v01_all_lr1e5") model = AutoModelForCausalLM.from_pretrained("lldois/v01_all_lr1e5", 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/v01_all_lr1e5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/v01_all_lr1e5" # 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/v01_all_lr1e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v01_all_lr1e5
- SGLang
How to use lldois/v01_all_lr1e5 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/v01_all_lr1e5" \ --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/v01_all_lr1e5", "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/v01_all_lr1e5" \ --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/v01_all_lr1e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v01_all_lr1e5 with Docker Model Runner:
docker model run hf.co/lldois/v01_all_lr1e5
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 398, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01256281407035176, | |
| "grad_norm": 45.75, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 2.9656538009643554, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02512562814070352, | |
| "grad_norm": 14.625, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 2.7247514724731445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03768844221105527, | |
| "grad_norm": 8.375, | |
| "learning_rate": 9.99933760728612e-06, | |
| "loss": 2.5403032302856445, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05025125628140704, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 9.991887704680723e-06, | |
| "loss": 2.3779970169067384, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06281407035175879, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 9.976172285185315e-06, | |
| "loss": 2.1928905487060546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07537688442211055, | |
| "grad_norm": 3.765625, | |
| "learning_rate": 9.952217370231655e-06, | |
| "loss": 2.082417106628418, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08793969849246232, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 9.920062624124282e-06, | |
| "loss": 1.9925090789794921, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10050251256281408, | |
| "grad_norm": 5.25, | |
| "learning_rate": 9.879761288364767e-06, | |
| "loss": 2.0241403579711914, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11306532663316583, | |
| "grad_norm": 3.234375, | |
| "learning_rate": 9.831380093494957e-06, | |
| "loss": 1.8994447708129882, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12562814070351758, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 9.77499914860525e-06, | |
| "loss": 1.8455327987670898, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13819095477386933, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 9.710711808690754e-06, | |
| "loss": 1.8259857177734375, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1507537688442211, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 9.638624520075047e-06, | |
| "loss": 1.8774749755859375, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16331658291457288, | |
| "grad_norm": 2.625, | |
| "learning_rate": 9.558856644157432e-06, | |
| "loss": 1.8711318969726562, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17587939698492464, | |
| "grad_norm": 2.875, | |
| "learning_rate": 9.471540259775554e-06, | |
| "loss": 1.804541778564453, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1884422110552764, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 9.376819944510598e-06, | |
| "loss": 1.7933189392089843, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20100502512562815, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 9.274852535297198e-06, | |
| "loss": 1.7203624725341797, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2135678391959799, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 9.165806868734444e-06, | |
| "loss": 1.7706247329711915, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22613065326633167, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 9.049863501527947e-06, | |
| "loss": 1.7302061080932618, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23869346733668342, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 8.927214411525895e-06, | |
| "loss": 1.7422285079956055, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25125628140703515, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 8.798062679844077e-06, | |
| "loss": 1.7749662399291992, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2638190954773869, | |
| "grad_norm": 2.375, | |
| "learning_rate": 8.662622154606238e-06, | |
| "loss": 1.6960893630981446, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.27638190954773867, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 8.521117096856529e-06, | |
| "loss": 1.663231086730957, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2889447236180904, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 8.373781809230355e-06, | |
| "loss": 1.6814579010009765, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3015075376884422, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 8.220860247998455e-06, | |
| "loss": 1.6490394592285156, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.314070351758794, | |
| "grad_norm": 2.5, | |
| "learning_rate": 8.062605619126585e-06, | |
| "loss": 1.6724288940429688, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.32663316582914576, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 7.899279959019654e-06, | |
| "loss": 1.7372112274169922, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3391959798994975, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 7.73115370064452e-06, | |
| "loss": 1.6612102508544921, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.35175879396984927, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 7.558505225749827e-06, | |
| "loss": 1.6610906600952149, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.36432160804020103, | |
| "grad_norm": 2.25, | |
| "learning_rate": 7.381620403924333e-06, | |
| "loss": 1.6504524230957032, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3768844221105528, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 7.200792119256961e-06, | |
| "loss": 1.6796260833740235, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38944723618090454, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 7.0163197853822975e-06, | |
| "loss": 1.6536401748657226, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.4020100502512563, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 6.828508849714546e-06, | |
| "loss": 1.6703350067138671, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.41457286432160806, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 6.6376702876908e-06, | |
| "loss": 1.658207321166992, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4271356783919598, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 6.444120087861081e-06, | |
| "loss": 1.6739206314086914, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4396984924623116, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 6.2481787286777116e-06, | |
| "loss": 1.679785919189453, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.45226130653266333, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 6.050170647850351e-06, | |
| "loss": 1.652729606628418, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4648241206030151, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 5.850423705145334e-06, | |
| "loss": 1.6558731079101563, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.47738693467336685, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 5.64926863951881e-06, | |
| "loss": 1.6815605163574219, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4899497487437186, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 5.447038521482542e-06, | |
| "loss": 1.7241903305053712, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5025125628140703, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 5.244068201609132e-06, | |
| "loss": 1.6395009994506835, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5150753768844221, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 5.040693756089865e-06, | |
| "loss": 1.6607843399047852, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5276381909547738, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 4.837251930263149e-06, | |
| "loss": 1.670051383972168, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5402010050251256, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 4.634079581035029e-06, | |
| "loss": 1.6406648635864258, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5527638190954773, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 4.431513119114934e-06, | |
| "loss": 1.7157506942749023, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5653266331658291, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 4.229887951990255e-06, | |
| "loss": 1.631689453125, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5778894472361809, | |
| "grad_norm": 2.125, | |
| "learning_rate": 4.029537928562028e-06, | |
| "loss": 1.6348350524902344, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5904522613065326, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 3.83079478636133e-06, | |
| "loss": 1.6371662139892578, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6030150753768844, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 3.633987602261647e-06, | |
| "loss": 1.6417142868041992, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6155778894472361, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 3.439442247596724e-06, | |
| "loss": 1.651812744140625, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.628140703517588, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 3.24748084858614e-06, | |
| "loss": 1.6704858779907226, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6407035175879398, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 3.0584212529619777e-06, | |
| "loss": 1.6126070022583008, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6532663316582915, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 2.872576503679789e-06, | |
| "loss": 1.650954246520996, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6658291457286433, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 2.6902543205852496e-06, | |
| "loss": 1.6697248458862304, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.678391959798995, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 2.511756590894765e-06, | |
| "loss": 1.66760311126709, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6909547738693468, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 2.3373788693337024e-06, | |
| "loss": 1.669024658203125, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7035175879396985, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 2.167409888759856e-06, | |
| "loss": 1.6077774047851563, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7160804020100503, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 2.002131082082549e-06, | |
| "loss": 1.5952661514282227, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7286432160804021, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.8418161162688613e-06, | |
| "loss": 1.6444393157958985, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7412060301507538, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.6867304392086575e-06, | |
| "loss": 1.661176872253418, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7537688442211056, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.5371308401886759e-06, | |
| "loss": 1.6453720092773438, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7663316582914573, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.393265024703422e-06, | |
| "loss": 1.627047348022461, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7788944723618091, | |
| "grad_norm": 3.125, | |
| "learning_rate": 1.255371204306956e-06, | |
| "loss": 1.6264894485473633, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7914572864321608, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.1236777021845957e-06, | |
| "loss": 1.6122165679931642, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8040201005025126, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 9.984025750977338e-07, | |
| "loss": 1.6706012725830077, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8165829145728644, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 8.797532523276542e-07, | |
| "loss": 1.6766525268554688, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8291457286432161, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 7.679261922162417e-07, | |
| "loss": 1.6081558227539063, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8417085427135679, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 6.631065568722633e-07, | |
| "loss": 1.661915397644043, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8542713567839196, | |
| "grad_norm": 2.75, | |
| "learning_rate": 5.654679055818202e-07, | |
| "loss": 1.6015464782714843, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8668341708542714, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 4.751719074306604e-07, | |
| "loss": 1.6529460906982423, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8793969849246231, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 3.923680736141411e-07, | |
| "loss": 1.6363981246948243, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8919597989949749, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 3.1719350987811537e-07, | |
| "loss": 1.6596275329589845, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.9045226130653267, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 2.497726895006353e-07, | |
| "loss": 1.6642751693725586, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9170854271356784, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.902172471903563e-07, | |
| "loss": 1.66651611328125, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9296482412060302, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 1.3862579424293366e-07, | |
| "loss": 1.6170860290527345, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9422110552763819, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 9.508375526142976e-08, | |
| "loss": 1.6495546340942382, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9547738693467337, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 5.966322671113523e-08, | |
| "loss": 1.6687738418579101, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9673366834170855, | |
| "grad_norm": 1.8828125, | |
| "learning_rate": 3.242285754296859e-08, | |
| "loss": 1.6350765228271484, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.9798994974874372, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.3407752083142155e-08, | |
| "loss": 1.6399044036865233, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.992462311557789, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 2.6493953498790692e-09, | |
| "loss": 1.7104473114013672, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 398, | |
| "total_flos": 1.9165347193492685e+17, | |
| "train_loss": 1.7490570976506525, | |
| "train_runtime": 3250.6471, | |
| "train_samples_per_second": 0.49, | |
| "train_steps_per_second": 0.122 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 398, | |
| "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 | |
| } | |