Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_5_moe
qwen3.5
Mixture of Experts
claude-distill
conversational
Instructions to use clzoro/Qwen3.5-35B-A3B-Claude-distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use clzoro/Qwen3.5-35B-A3B-Claude-distill with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="clzoro/Qwen3.5-35B-A3B-Claude-distill") 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)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("clzoro/Qwen3.5-35B-A3B-Claude-distill") model = AutoModelForMultimodalLM.from_pretrained("clzoro/Qwen3.5-35B-A3B-Claude-distill", 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=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use clzoro/Qwen3.5-35B-A3B-Claude-distill with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "clzoro/Qwen3.5-35B-A3B-Claude-distill" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "clzoro/Qwen3.5-35B-A3B-Claude-distill", "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/clzoro/Qwen3.5-35B-A3B-Claude-distill
- SGLang
How to use clzoro/Qwen3.5-35B-A3B-Claude-distill 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 "clzoro/Qwen3.5-35B-A3B-Claude-distill" \ --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": "clzoro/Qwen3.5-35B-A3B-Claude-distill", "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 "clzoro/Qwen3.5-35B-A3B-Claude-distill" \ --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": "clzoro/Qwen3.5-35B-A3B-Claude-distill", "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 clzoro/Qwen3.5-35B-A3B-Claude-distill with Docker Model Runner:
docker model run hf.co/clzoro/Qwen3.5-35B-A3B-Claude-distill
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 200.0, | |
| "global_step": 370, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005405405405405406, | |
| "grad_norm": 3.1680717633202877, | |
| "learning_rate": 1.5789473684210526e-06, | |
| "loss": 0.6688475608825684, | |
| "step": 1, | |
| "token_acc": 0.8242903529904682 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 1.8549251728609573, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 0.8109264373779297, | |
| "step": 10, | |
| "token_acc": 0.7761103592601787 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 0.9484813990147456, | |
| "learning_rate": 2.9999399180697783e-05, | |
| "loss": 0.6205739498138427, | |
| "step": 20, | |
| "token_acc": 0.8202673243249641 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 1.183614904613414, | |
| "learning_rate": 2.9927359084964877e-05, | |
| "loss": 0.6088469982147217, | |
| "step": 30, | |
| "token_acc": 0.8198438348312171 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 1.2353384024615621, | |
| "learning_rate": 2.973581606123497e-05, | |
| "loss": 0.739194393157959, | |
| "step": 40, | |
| "token_acc": 0.7898660420316513 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 1.3432923315535181, | |
| "learning_rate": 2.942630353226844e-05, | |
| "loss": 0.6011062622070312, | |
| "step": 50, | |
| "token_acc": 0.8247190588471379 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 1.168183989145606, | |
| "learning_rate": 2.900129934114876e-05, | |
| "loss": 0.6731441020965576, | |
| "step": 60, | |
| "token_acc": 0.8113857485368042 | |
| }, | |
| { | |
| "epoch": 0.3783783783783784, | |
| "grad_norm": 1.2344777400050695, | |
| "learning_rate": 2.8464205914585212e-05, | |
| "loss": 0.6012222290039062, | |
| "step": 70, | |
| "token_acc": 0.8260620662270369 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 1.16232118124639, | |
| "learning_rate": 2.7819323024340304e-05, | |
| "loss": 0.6182085990905761, | |
| "step": 80, | |
| "token_acc": 0.8235405045953511 | |
| }, | |
| { | |
| "epoch": 0.4864864864864865, | |
| "grad_norm": 0.9498735816994268, | |
| "learning_rate": 2.7071813364843832e-05, | |
| "loss": 0.59684157371521, | |
| "step": 90, | |
| "token_acc": 0.8311607063059382 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 0.8108342228004247, | |
| "learning_rate": 2.6227661222566516e-05, | |
| "loss": 0.6133281230926514, | |
| "step": 100, | |
| "token_acc": 0.8260576887809151 | |
| }, | |
| { | |
| "epoch": 0.5945945945945946, | |
| "grad_norm": 1.2084724906810802, | |
| "learning_rate": 2.5293624568031008e-05, | |
| "loss": 0.5700843811035157, | |
| "step": 110, | |
| "token_acc": 0.8353099803946354 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 1.1407595512042275, | |
| "learning_rate": 2.4277180953993826e-05, | |
| "loss": 0.585970115661621, | |
| "step": 120, | |
| "token_acc": 0.8267323572461026 | |
| }, | |
| { | |
| "epoch": 0.7027027027027027, | |
| "grad_norm": 1.230613842801466, | |
| "learning_rate": 2.318646765291757e-05, | |
| "loss": 0.6366302967071533, | |
| "step": 130, | |
| "token_acc": 0.8218803207769427 | |
| }, | |
| { | |
| "epoch": 0.7567567567567568, | |
| "grad_norm": 1.2394471459646628, | |
| "learning_rate": 2.2030216512970554e-05, | |
| "loss": 0.5958713531494141, | |
| "step": 140, | |
| "token_acc": 0.8305702226808576 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 1.1136999131785847, | |
| "learning_rate": 2.0817684054072827e-05, | |
| "loss": 0.7051344871520996, | |
| "step": 150, | |
| "token_acc": 0.7948495053253495 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.953872013030958, | |
| "learning_rate": 1.9558577363613704e-05, | |
| "loss": 0.5482869148254395, | |
| "step": 160, | |
| "token_acc": 0.8431717927114541 | |
| }, | |
| { | |
| "epoch": 0.918918918918919, | |
| "grad_norm": 1.1211814795042592, | |
| "learning_rate": 1.826297638509251e-05, | |
| "loss": 0.6120530128479004, | |
| "step": 170, | |
| "token_acc": 0.825810897386503 | |
| }, | |
| { | |
| "epoch": 0.972972972972973, | |
| "grad_norm": 1.0724707419323103, | |
| "learning_rate": 1.694125322181083e-05, | |
| "loss": 0.6729551792144776, | |
| "step": 180, | |
| "token_acc": 0.809713255234503 | |
| }, | |
| { | |
| "epoch": 1.027027027027027, | |
| "grad_norm": 0.9017702538446655, | |
| "learning_rate": 1.5603989101641228e-05, | |
| "loss": 0.49294071197509765, | |
| "step": 190, | |
| "token_acc": 0.8595634401529221 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.8357826808926182, | |
| "learning_rate": 1.4261889667621828e-05, | |
| "loss": 0.30256004333496095, | |
| "step": 200, | |
| "token_acc": 0.9047140790097637 | |
| }, | |
| { | |
| "epoch": 1.135135135135135, | |
| "grad_norm": 1.3306024060830839, | |
| "learning_rate": 1.2925699272529006e-05, | |
| "loss": 0.28004865646362304, | |
| "step": 210, | |
| "token_acc": 0.9124356333016044 | |
| }, | |
| { | |
| "epoch": 1.1891891891891893, | |
| "grad_norm": 1.0315509694012732, | |
| "learning_rate": 1.1606114963554171e-05, | |
| "loss": 0.28960094451904295, | |
| "step": 220, | |
| "token_acc": 0.9050426736039798 | |
| }, | |
| { | |
| "epoch": 1.2432432432432432, | |
| "grad_norm": 0.897647555480616, | |
| "learning_rate": 1.0313700845691636e-05, | |
| "loss": 0.24299814701080322, | |
| "step": 230, | |
| "token_acc": 0.9234494029347422 | |
| }, | |
| { | |
| "epoch": 1.2972972972972974, | |
| "grad_norm": 1.0238680932300175, | |
| "learning_rate": 9.058803509412647e-06, | |
| "loss": 0.2083221435546875, | |
| "step": 240, | |
| "token_acc": 0.9324800906289405 | |
| }, | |
| { | |
| "epoch": 1.3513513513513513, | |
| "grad_norm": 0.8507949565744011, | |
| "learning_rate": 7.851469199680382e-06, | |
| "loss": 0.27800228595733645, | |
| "step": 250, | |
| "token_acc": 0.9101957597480809 | |
| }, | |
| { | |
| "epoch": 1.4054054054054055, | |
| "grad_norm": 0.9239797828529825, | |
| "learning_rate": 6.701363389420296e-06, | |
| "loss": 0.257454514503479, | |
| "step": 260, | |
| "token_acc": 0.9200535757981635 | |
| }, | |
| { | |
| "epoch": 1.4594594594594594, | |
| "grad_norm": 0.8289302773930988, | |
| "learning_rate": 5.617693401310837e-06, | |
| "loss": 0.2699479103088379, | |
| "step": 270, | |
| "token_acc": 0.9118848637175058 | |
| }, | |
| { | |
| "epoch": 1.5135135135135136, | |
| "grad_norm": 1.4264660137512906, | |
| "learning_rate": 4.609134697356009e-06, | |
| "loss": 0.25818724632263185, | |
| "step": 280, | |
| "token_acc": 0.9165730954889045 | |
| }, | |
| { | |
| "epoch": 1.5675675675675675, | |
| "grad_norm": 0.6809121084776086, | |
| "learning_rate": 3.683761426338148e-06, | |
| "loss": 0.2499394655227661, | |
| "step": 290, | |
| "token_acc": 0.9210303247829308 | |
| }, | |
| { | |
| "epoch": 1.6216216216216215, | |
| "grad_norm": 0.7911442310830548, | |
| "learning_rate": 2.848981785162503e-06, | |
| "loss": 0.2243581771850586, | |
| "step": 300, | |
| "token_acc": 0.9255768284539416 | |
| }, | |
| { | |
| "epoch": 1.6756756756756757, | |
| "grad_norm": 0.8302748471075124, | |
| "learning_rate": 2.1114787115667476e-06, | |
| "loss": 0.2524730205535889, | |
| "step": 310, | |
| "token_acc": 0.9196754182044243 | |
| }, | |
| { | |
| "epoch": 1.7297297297297298, | |
| "grad_norm": 0.7652465806020483, | |
| "learning_rate": 1.4771563829877598e-06, | |
| "loss": 0.21740343570709228, | |
| "step": 320, | |
| "token_acc": 0.9257807174001964 | |
| }, | |
| { | |
| "epoch": 1.7837837837837838, | |
| "grad_norm": 0.6723695635268157, | |
| "learning_rate": 9.51092949895927e-07, | |
| "loss": 0.29862112998962403, | |
| "step": 330, | |
| "token_acc": 0.9064944202025343 | |
| }, | |
| { | |
| "epoch": 1.8378378378378377, | |
| "grad_norm": 0.7836833639138061, | |
| "learning_rate": 5.374998819965654e-07, | |
| "loss": 0.2673323154449463, | |
| "step": 340, | |
| "token_acc": 0.9137580442481246 | |
| }, | |
| { | |
| "epoch": 1.8918918918918919, | |
| "grad_norm": 0.8148712923768102, | |
| "learning_rate": 2.3968825275764774e-07, | |
| "loss": 0.2481457471847534, | |
| "step": 350, | |
| "token_acc": 0.9221015450205239 | |
| }, | |
| { | |
| "epoch": 1.945945945945946, | |
| "grad_norm": 1.055375940725962, | |
| "learning_rate": 6.00422321775751e-08, | |
| "loss": 0.2384178876876831, | |
| "step": 360, | |
| "token_acc": 0.9246336357292394 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.9495217159079454, | |
| "learning_rate": 0.0, | |
| "loss": 0.22227826118469238, | |
| "step": 370, | |
| "token_acc": 0.9248096999252118 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 370, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 163536917889024.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |