Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
Generated from Trainer
R1-V
trl
sft
conversational
text-generation-inference
Instructions to use Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink") model = AutoModelForMultimodalLM.from_pretrained("Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink
- SGLang
How to use Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink 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 "Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink" \ --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": "Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink" \ --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": "Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink with Docker Model Runner:
docker model run hf.co/Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink
Download trainer_state.json from Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink: direct link, hf CLI and curl.
- Browser
- Download file 8.7 kB
-
https://huggingface.co/Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink/resolve/main/trainer_state.json
- Command line
-
hf download hf://Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Leeyuyu/Qwen2.5-SFT-GRPO-fundo-nothink/resolve/main/trainer_state.json
8.7 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 818.252685546875, | |
| "learning_rate": 4e-08, | |
| "loss": 8.0825, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 818.1897583007812, | |
| "learning_rate": 8e-08, | |
| "loss": 8.083, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 818.9984741210938, | |
| "learning_rate": 1.2e-07, | |
| "loss": 8.0738, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 814.5826416015625, | |
| "learning_rate": 1.6e-07, | |
| "loss": 8.0586, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 818.0709838867188, | |
| "learning_rate": 2e-07, | |
| "loss": 8.0518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 820.11474609375, | |
| "learning_rate": 1.997564050259824e-07, | |
| "loss": 8.0655, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 813.5534057617188, | |
| "learning_rate": 1.9902680687415702e-07, | |
| "loss": 8.0512, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 813.9736938476562, | |
| "learning_rate": 1.9781476007338056e-07, | |
| "loss": 8.0414, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 810.3634033203125, | |
| "learning_rate": 1.9612616959383187e-07, | |
| "loss": 7.9481, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 811.2542114257812, | |
| "learning_rate": 1.9396926207859085e-07, | |
| "loss": 7.9573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 810.1604614257812, | |
| "learning_rate": 1.9135454576426007e-07, | |
| "loss": 7.9447, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 816.74462890625, | |
| "learning_rate": 1.8829475928589268e-07, | |
| "loss": 7.9186, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 811.1762084960938, | |
| "learning_rate": 1.8480480961564257e-07, | |
| "loss": 7.9079, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 790.3859252929688, | |
| "learning_rate": 1.8090169943749475e-07, | |
| "loss": 7.654, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 798.2161254882812, | |
| "learning_rate": 1.766044443118978e-07, | |
| "loss": 7.6624, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 792.4284057617188, | |
| "learning_rate": 1.719339800338651e-07, | |
| "loss": 7.6362, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 797.7490844726562, | |
| "learning_rate": 1.669130606358858e-07, | |
| "loss": 7.8007, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 792.290771484375, | |
| "learning_rate": 1.615661475325658e-07, | |
| "loss": 7.6444, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 791.4799194335938, | |
| "learning_rate": 1.5591929034707466e-07, | |
| "loss": 7.6096, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 781.8382568359375, | |
| "learning_rate": 1.5e-07, | |
| "loss": 7.5249, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 787.5663452148438, | |
| "learning_rate": 1.4383711467890774e-07, | |
| "loss": 7.5302, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 787.5963745117188, | |
| "learning_rate": 1.374606593415912e-07, | |
| "loss": 7.5086, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 785.0594482421875, | |
| "learning_rate": 1.3090169943749475e-07, | |
| "loss": 7.5495, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 783.998291015625, | |
| "learning_rate": 1.2419218955996676e-07, | |
| "loss": 7.5004, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 785.1058349609375, | |
| "learning_rate": 1.1736481776669305e-07, | |
| "loss": 7.5234, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 713.4159545898438, | |
| "learning_rate": 1.1045284632676535e-07, | |
| "loss": 6.7809, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 707.8865356445312, | |
| "learning_rate": 1.0348994967025011e-07, | |
| "loss": 6.6029, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 708.47412109375, | |
| "learning_rate": 9.651005032974993e-08, | |
| "loss": 6.5739, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 702.1832275390625, | |
| "learning_rate": 8.954715367323466e-08, | |
| "loss": 6.5528, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 707.9276733398438, | |
| "learning_rate": 8.263518223330696e-08, | |
| "loss": 6.5052, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 706.7056884765625, | |
| "learning_rate": 7.580781044003323e-08, | |
| "loss": 6.5264, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 701.0953979492188, | |
| "learning_rate": 6.909830056250527e-08, | |
| "loss": 6.54, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 702.4327392578125, | |
| "learning_rate": 6.253934065840879e-08, | |
| "loss": 6.5456, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 700.1629638671875, | |
| "learning_rate": 5.616288532109225e-08, | |
| "loss": 6.4829, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 700.8172607421875, | |
| "learning_rate": 5.000000000000002e-08, | |
| "loss": 6.4659, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 704.9315795898438, | |
| "learning_rate": 4.408070965292533e-08, | |
| "loss": 6.5499, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 703.9114990234375, | |
| "learning_rate": 3.843385246743417e-08, | |
| "loss": 6.4908, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 701.8934936523438, | |
| "learning_rate": 3.3086939364114206e-08, | |
| "loss": 6.4915, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 695.6119384765625, | |
| "learning_rate": 2.8066019966134903e-08, | |
| "loss": 6.4808, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 697.15625, | |
| "learning_rate": 2.339555568810221e-08, | |
| "loss": 6.4609, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 696.0047607421875, | |
| "learning_rate": 1.9098300562505266e-08, | |
| "loss": 6.4469, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 703.1214599609375, | |
| "learning_rate": 1.5195190384357405e-08, | |
| "loss": 6.4827, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 697.6890258789062, | |
| "learning_rate": 1.1705240714107301e-08, | |
| "loss": 6.4773, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 697.1249389648438, | |
| "learning_rate": 8.645454235739902e-09, | |
| "loss": 6.4647, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 698.1083984375, | |
| "learning_rate": 6.030737921409168e-09, | |
| "loss": 6.4785, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 699.7293701171875, | |
| "learning_rate": 3.873830406168111e-09, | |
| "loss": 6.4605, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 697.2705688476562, | |
| "learning_rate": 2.1852399266194312e-09, | |
| "loss": 6.4725, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 699.6365966796875, | |
| "learning_rate": 9.731931258429638e-10, | |
| "loss": 6.4544, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 698.3743896484375, | |
| "learning_rate": 2.4359497401758025e-10, | |
| "loss": 6.4655, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 696.75634765625, | |
| "learning_rate": 0.0, | |
| "loss": 6.4721, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 50, | |
| "total_flos": 1.127911562149888e+17, | |
| "train_loss": 7.161082897186279, | |
| "train_runtime": 995.3533, | |
| "train_samples_per_second": 3.21, | |
| "train_steps_per_second": 0.05 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.127911562149888e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |