Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v17_item_caption_cot_lr13e6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v17_item_caption_cot_lr13e6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v17_item_caption_cot_lr13e6") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/v17_item_caption_cot_lr13e6") model = AutoModelForCausalLM.from_pretrained("lldois/v17_item_caption_cot_lr13e6", 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/v17_item_caption_cot_lr13e6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/v17_item_caption_cot_lr13e6" # 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/v17_item_caption_cot_lr13e6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v17_item_caption_cot_lr13e6
- SGLang
How to use lldois/v17_item_caption_cot_lr13e6 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/v17_item_caption_cot_lr13e6" \ --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/v17_item_caption_cot_lr13e6", "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/v17_item_caption_cot_lr13e6" \ --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/v17_item_caption_cot_lr13e6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v17_item_caption_cot_lr13e6 with Docker Model Runner:
docker model run hf.co/lldois/v17_item_caption_cot_lr13e6
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 423, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011841326228537596, | |
| "grad_norm": 44.75, | |
| "learning_rate": 4e-06, | |
| "loss": 2.976611328125, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023682652457075192, | |
| "grad_norm": 12.25, | |
| "learning_rate": 8.999999999999999e-06, | |
| "loss": 2.77978572845459, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.035523978685612786, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 1.2999809184667674e-05, | |
| "loss": 2.5306840896606446, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.047365304914150384, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.2993131824301589e-05, | |
| "loss": 2.2824148178100585, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05920663114268798, | |
| "grad_norm": 3.453125, | |
| "learning_rate": 1.297692489759098e-05, | |
| "loss": 2.1631048202514647, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07104795737122557, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 1.2951212190435705e-05, | |
| "loss": 2.0169919967651366, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08288928359976318, | |
| "grad_norm": 3.375, | |
| "learning_rate": 1.2916031439779258e-05, | |
| "loss": 1.9718114852905273, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09473060982830077, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.2871434278224593e-05, | |
| "loss": 1.9569698333740235, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10657193605683836, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.281748615825617e-05, | |
| "loss": 1.889408493041992, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11841326228537596, | |
| "grad_norm": 3.40625, | |
| "learning_rate": 1.2754266256179397e-05, | |
| "loss": 1.8037897109985352, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13025458851391356, | |
| "grad_norm": 3.953125, | |
| "learning_rate": 1.2681867355918499e-05, | |
| "loss": 1.820526123046875, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14209591474245115, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.2600395712843294e-05, | |
| "loss": 1.7561323165893554, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15393724097098876, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.2509970897824807e-05, | |
| "loss": 1.813785934448242, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16577856719952636, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.241072562174851e-05, | |
| "loss": 1.7308807373046875, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17761989342806395, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.230280554074281e-05, | |
| "loss": 1.6870466232299806, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18946121965660154, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.218636904240859e-05, | |
| "loss": 1.6947086334228516, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20130254588513913, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 1.2061587013363553e-05, | |
| "loss": 1.6740726470947265, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.21314387211367672, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.1928642588442567e-05, | |
| "loss": 1.6932085037231446, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22498519834221434, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 1.1787730881922022e-05, | |
| "loss": 1.6984859466552735, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.23682652457075193, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 1.1639058701162737e-05, | |
| "loss": 1.6615169525146485, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24866785079928952, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 1.1482844243091624e-05, | |
| "loss": 1.629263687133789, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2605091770278271, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.1319316773967625e-05, | |
| "loss": 1.7143014907836913, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27235050325636473, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 1.1148716292901853e-05, | |
| "loss": 1.648763656616211, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2841918294849023, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.0971293179625803e-05, | |
| "loss": 1.6492090225219727, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2960331557134399, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.0787307827024565e-05, | |
| "loss": 1.6368392944335937, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.30787448194197753, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.0597030258974366e-05, | |
| "loss": 1.6719234466552735, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3197158081705151, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.0400739734045288e-05, | |
| "loss": 1.6404973983764648, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3315571343990527, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.0198724335650807e-05, | |
| "loss": 1.6293134689331055, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3433984606275903, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 9.991280549245664e-06, | |
| "loss": 1.6447383880615234, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3552397868561279, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 9.778712827192572e-06, | |
| "loss": 1.6770294189453125, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.36708111308466546, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 9.561333141936387e-06, | |
| "loss": 1.5788751602172852, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.3789224393132031, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 9.33946052814153e-06, | |
| "loss": 1.5903149604797364, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3907637655417407, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 9.113420614464618e-06, | |
| "loss": 1.6232831954956055, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.40260509177027826, | |
| "grad_norm": 2.125, | |
| "learning_rate": 8.883545145649511e-06, | |
| "loss": 1.5795005798339843, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4144464179988159, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 8.65017149564615e-06, | |
| "loss": 1.6659164428710938, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.42628774422735344, | |
| "grad_norm": 2.25, | |
| "learning_rate": 8.41364217246776e-06, | |
| "loss": 1.6965517044067382, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43812907045589106, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 8.174304315513122e-06, | |
| "loss": 1.5858169555664063, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.4499703966844287, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 7.932509186091612e-06, | |
| "loss": 1.6201683044433595, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.46181172291296624, | |
| "grad_norm": 2.25, | |
| "learning_rate": 7.68861165189882e-06, | |
| "loss": 1.6074403762817382, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.47365304914150386, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 7.442969666199241e-06, | |
| "loss": 1.617002296447754, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4854943753700414, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 7.195943742480528e-06, | |
| "loss": 1.6207464218139649, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.49733570159857904, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 6.94789642535021e-06, | |
| "loss": 1.6103069305419921, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5091770278271166, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 6.6991917584515e-06, | |
| "loss": 1.5691112518310546, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5210183540556542, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 6.450194750179039e-06, | |
| "loss": 1.6248830795288085, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5328596802841918, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 6.201270837978755e-06, | |
| "loss": 1.561983585357666, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5447010065127295, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 5.952785352018004e-06, | |
| "loss": 1.588427734375, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5565423327412671, | |
| "grad_norm": 2.0, | |
| "learning_rate": 5.705102979013181e-06, | |
| "loss": 1.6155115127563477, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.5683836589698046, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 5.458587227001667e-06, | |
| "loss": 1.5733617782592773, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5802249851983422, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 5.213599891843665e-06, | |
| "loss": 1.5730903625488282, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.5920663114268798, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 4.970500526236871e-06, | |
| "loss": 1.5600762367248535, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6039076376554174, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 4.729645912023323e-06, | |
| "loss": 1.610726547241211, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6157489638839551, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 4.4913895365628424e-06, | |
| "loss": 1.5865031242370606, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6275902901124926, | |
| "grad_norm": 2.0, | |
| "learning_rate": 4.256081073941585e-06, | |
| "loss": 1.603274154663086, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6394316163410302, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 4.0240658717771024e-06, | |
| "loss": 1.600333023071289, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6512729425695678, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 3.7956844443730916e-06, | |
| "loss": 1.5704521179199218, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6631142687981054, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 3.5712719729676987e-06, | |
| "loss": 1.5828316688537598, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6749555950266429, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 3.351157813808825e-06, | |
| "loss": 1.5770600318908692, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.6867969212551805, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 3.1356650147784227e-06, | |
| "loss": 1.593960666656494, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6986382474837182, | |
| "grad_norm": 1.9609375, | |
| "learning_rate": 2.9251098412751775e-06, | |
| "loss": 1.580451774597168, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7104795737122558, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 2.719801312051425e-06, | |
| "loss": 1.614090347290039, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7223208999407934, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 2.5200407456855087e-06, | |
| "loss": 1.5809415817260741, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7341622261693309, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 2.3261213183552334e-06, | |
| "loss": 1.553083324432373, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7460035523978685, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 2.1383276335613797e-06, | |
| "loss": 1.6024253845214844, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.7578448786264061, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.9569353044328275e-06, | |
| "loss": 1.5699667930603027, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7696862048549438, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.7822105492262824e-06, | |
| "loss": 1.608834457397461, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7815275310834814, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.614409800614272e-06, | |
| "loss": 1.5530618667602538, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7933688573120189, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.4537793293348317e-06, | |
| "loss": 1.6589471817016601, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8052101835405565, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.300554882755248e-06, | |
| "loss": 1.6034730911254882, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8170515097690941, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.1549613388802793e-06, | |
| "loss": 1.6377271652221679, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8288928359976317, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 1.0172123763126773e-06, | |
| "loss": 1.6403684616088867, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8407341622261694, | |
| "grad_norm": 1.859375, | |
| "learning_rate": 8.875101606503659e-07, | |
| "loss": 1.5954139709472657, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.8525754884547069, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 7.660450477805567e-07, | |
| "loss": 1.5502955436706543, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8644168146832445, | |
| "grad_norm": 1.890625, | |
| "learning_rate": 6.529953045062282e-07, | |
| "loss": 1.5533514976501466, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.8762581409117821, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 5.485268469150119e-07, | |
| "loss": 1.5953169822692872, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8880994671403197, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 4.5279299687445366e-07, | |
| "loss": 1.5968003273010254, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8999407933688574, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 3.659342570110326e-07, | |
| "loss": 1.5658743858337403, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9117821195973949, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 2.880781045031754e-07, | |
| "loss": 1.5887388229370116, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.9236234458259325, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 2.1933880399092585e-07, | |
| "loss": 1.5834945678710937, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9354647720544701, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 1.5981723987682304e-07, | |
| "loss": 1.5624884605407714, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.9473060982830077, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.09600768264133e-07, | |
| "loss": 1.6257368087768556, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9591474245115453, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 6.876308874971658e-08, | |
| "loss": 1.5857719421386718, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.9709887507400828, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 3.736413625971091e-08, | |
| "loss": 1.5751670837402343, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9828300769686205, | |
| "grad_norm": 1.9140625, | |
| "learning_rate": 1.544999308676015e-08, | |
| "loss": 1.6034950256347655, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.9946714031971581, | |
| "grad_norm": 3.640625, | |
| "learning_rate": 3.052821257894633e-09, | |
| "loss": 1.5355438232421874, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 423, | |
| "total_flos": 2.0218118019963494e+17, | |
| "train_loss": 1.6924350921143876, | |
| "train_runtime": 3361.2318, | |
| "train_samples_per_second": 0.502, | |
| "train_steps_per_second": 0.126 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 423, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0218118019963494e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |