Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
camera-movement
video-understanding
qwen3-vl
sft
Instructions to use ddz16/CamSFT-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ddz16/CamSFT-8B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ddz16/CamSFT-8B") model = AutoModelForMultimodalLM.from_pretrained("ddz16/CamSFT-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "per_device_train_batch_size": 2, | |
| "num_train_epochs": 2.0, | |
| "max_steps": -1, | |
| "learning_rate": 1.5e-05, | |
| "lr_scheduler_type": "cosine", | |
| "lr_scheduler_kwargs": null, | |
| "warmup_steps": 0, | |
| "optim": "adamw_torch_fused", | |
| "optim_args": null, | |
| "weight_decay": 0.01, | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.95, | |
| "adam_epsilon": 1e-08, | |
| "optim_target_modules": null, | |
| "gradient_accumulation_steps": 4, | |
| "average_tokens_across_devices": true, | |
| "max_grad_norm": 1.0, | |
| "label_smoothing_factor": 0.0, | |
| "bf16": true, | |
| "fp16": false, | |
| "bf16_full_eval": false, | |
| "fp16_full_eval": false, | |
| "tf32": null, | |
| "gradient_checkpointing": true, | |
| "gradient_checkpointing_kwargs": null, | |
| "torch_compile": false, | |
| "torch_compile_backend": null, | |
| "torch_compile_mode": null, | |
| "use_liger_kernel": false, | |
| "liger_kernel_config": null, | |
| "use_cache": false, | |
| "neftune_noise_alpha": null, | |
| "torch_empty_cache_steps": null, | |
| "auto_find_batch_size": false, | |
| "logging_strategy": "steps", | |
| "logging_steps": 10, | |
| "logging_first_step": true, | |
| "log_on_each_node": true, | |
| "logging_nan_inf_filter": true, | |
| "include_num_input_tokens_seen": false, | |
| "log_level": "passive", | |
| "log_level_replica": "warning", | |
| "disable_tqdm": null, | |
| "report_to": [ | |
| "wandb" | |
| ], | |
| "project": "huggingface", | |
| "trackio_space_id": null, | |
| "trackio_bucket_id": null, | |
| "trackio_static_space_id": null, | |
| "eval_strategy": "no", | |
| "eval_steps": null, | |
| "eval_delay": 0, | |
| "per_device_eval_batch_size": 2, | |
| "prediction_loss_only": false, | |
| "eval_on_start": false, | |
| "eval_do_concat_batches": true, | |
| "eval_use_gather_object": false, | |
| "eval_accumulation_steps": null, | |
| "include_for_metrics": [], | |
| "batch_eval_metrics": false, | |
| "save_only_model": false, | |
| "save_strategy": "epoch", | |
| "save_steps": 500, | |
| "save_on_each_node": false, | |
| "save_total_limit": 1, | |
| "enable_jit_checkpoint": false, | |
| "push_to_hub": false, | |
| "hub_token": null, | |
| "hub_private_repo": null, | |
| "hub_model_id": null, | |
| "hub_strategy": "every_save", | |
| "hub_always_push": false, | |
| "hub_revision": null, | |
| "load_best_model_at_end": false, | |
| "metric_for_best_model": "loss", | |
| "greater_is_better": false, | |
| "ignore_data_skip": false, | |
| "restore_callback_states_from_checkpoint": false, | |
| "full_determinism": false, | |
| "seed": 42, | |
| "data_seed": 42, | |
| "use_cpu": false, | |
| "accelerator_config": { | |
| "dispatch_batches": false | |
| }, | |
| "parallelism_config": null, | |
| "dataloader_drop_last": false, | |
| "dataloader_num_workers": 8, | |
| "dataloader_pin_memory": true, | |
| "dataloader_persistent_workers": false, | |
| "dataloader_prefetch_factor": null, | |
| "remove_unused_columns": true, | |
| "label_names": null, | |
| "train_sampling_strategy": "random", | |
| "length_column_name": "length", | |
| "ddp_find_unused_parameters": null, | |
| "ddp_bucket_cap_mb": null, | |
| "ddp_broadcast_buffers": null, | |
| "ddp_static_graph": null, | |
| "ddp_backend": null, | |
| "ddp_timeout": 18000000, | |
| "fsdp": [], | |
| "fsdp_config": null, | |
| "deepspeed": { | |
| "fp16": { | |
| "enabled": "auto", | |
| "loss_scale": 0, | |
| "loss_scale_window": 1000, | |
| "initial_scale_power": 16, | |
| "hysteresis": 2, | |
| "min_loss_scale": 1 | |
| }, | |
| "bf16": { | |
| "enabled": "auto" | |
| }, | |
| "zero_optimization": { | |
| "stage": 2, | |
| "offload_optimizer": { | |
| "device": "none", | |
| "pin_memory": true | |
| }, | |
| "allgather_partitions": true, | |
| "allgather_bucket_size": 200000000.0, | |
| "overlap_comm": false, | |
| "reduce_scatter": true, | |
| "reduce_bucket_size": 200000000.0, | |
| "contiguous_gradients": true | |
| }, | |
| "gradient_accumulation_steps": "auto", | |
| "gradient_clipping": "auto", | |
| "steps_per_print": 2000, | |
| "train_batch_size": "auto", | |
| "train_micro_batch_size_per_gpu": "auto", | |
| "wall_clock_breakdown": false | |
| }, | |
| "debug": null, | |
| "skip_memory_metrics": true, | |
| "do_train": false, | |
| "do_eval": false, | |
| "do_predict": false, | |
| "resume_from_checkpoint": null, | |
| "warmup_ratio": 0.05, | |
| "local_rank": 0, | |
| "sortish_sampler": false, | |
| "predict_with_generate": false, | |
| "generation_max_length": null, | |
| "generation_num_beams": null, | |
| "generation_config": null, | |
| "tuner_backend": "peft", | |
| "vit_gradient_checkpointing": false, | |
| "router_aux_loss_coef": 0.0, | |
| "enable_dft_loss": false, | |
| "enable_channel_loss": false, | |
| "safe_serialization": true, | |
| "max_shard_size": "5GB", | |
| "check_model": true, | |
| "acc_strategy": "token", | |
| "train_dataloader_shuffle": true, | |
| "group_by_length": false, | |
| "max_epochs": null, | |
| "aligner_lr": null, | |
| "vit_lr": null, | |
| "use_logits_to_keep": null, | |
| "ds3_gather_for_generation": true, | |
| "resume_only_model": false, | |
| "optimizer": null, | |
| "loss_type": null, | |
| "eval_metric": null, | |
| "callbacks": [], | |
| "early_stop_interval": null, | |
| "eval_use_evalscope": false, | |
| "eval_dataset": [], | |
| "eval_dataset_args": null, | |
| "eval_limit": null, | |
| "eval_generation_config": null, | |
| "extra_eval_args": null, | |
| "tuner_type": "full", | |
| "use_galore": false, | |
| "galore_target_modules": null, | |
| "galore_rank": 128, | |
| "galore_update_proj_gap": 50, | |
| "galore_scale": 1.0, | |
| "galore_proj_type": "std", | |
| "galore_optim_per_parameter": false, | |
| "galore_with_embedding": false, | |
| "galore_quantization": false, | |
| "galore_proj_quant": false, | |
| "galore_proj_bits": 4, | |
| "galore_proj_group_size": 256, | |
| "galore_cos_threshold": 0.4, | |
| "galore_gamma_proj": 2, | |
| "galore_queue_size": 5, | |
| "lisa_activated_layers": 0, | |
| "lisa_step_interval": 20, | |
| "use_flash_ckpt": false, | |
| "use_ray": false, | |
| "ray_exp_name": null, | |
| "device_groups": null, | |
| "model": "Qwen/Qwen3-VL-8B-Instruct", | |
| "model_type": "qwen3_vl", | |
| "model_revision": null, | |
| "task_type": "causal_lm", | |
| "torch_dtype": "bfloat16", | |
| "attn_impl": "flash_attention_2", | |
| "experts_impl": null, | |
| "new_special_tokens": [], | |
| "num_labels": null, | |
| "problem_type": null, | |
| "rope_scaling": null, | |
| "device_map": null, | |
| "max_memory": {}, | |
| "max_model_len": null, | |
| "local_repo_path": null, | |
| "init_strategy": null, | |
| "template": "qwen3_vl", | |
| "system": null, | |
| "max_length": 16384, | |
| "truncation_strategy": "delete", | |
| "max_pixels": null, | |
| "agent_template": null, | |
| "norm_bbox": null, | |
| "use_chat_template": true, | |
| "padding_side": "right", | |
| "padding_free": false, | |
| "loss_scale": "default", | |
| "sequence_parallel_size": 1, | |
| "template_backend": "swift", | |
| "response_prefix": null, | |
| "enable_thinking": null, | |
| "preserve_thinking": null, | |
| "add_non_thinking_prefix": true, | |
| "val_dataset": [], | |
| "cached_dataset": [], | |
| "cached_val_dataset": [], | |
| "split_dataset_ratio": 0.0, | |
| "dataset_num_proc": 8, | |
| "load_from_cache_file": true, | |
| "dataset_shuffle": true, | |
| "val_dataset_shuffle": false, | |
| "streaming": false, | |
| "interleave_prob": null, | |
| "stopping_strategy": "first_exhausted", | |
| "shuffle_buffer_size": 1000, | |
| "download_mode": "reuse_dataset_if_exists", | |
| "columns": {}, | |
| "strict": false, | |
| "disable_auto_column_mapping": false, | |
| "model_name": null, | |
| "model_author": null, | |
| "custom_dataset_info": [], | |
| "quant_method": null, | |
| "quant_bits": null, | |
| "hqq_axis": null, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "bnb_4bit_quant_storage": null, | |
| "max_new_tokens": 64, | |
| "temperature": 0.0, | |
| "top_k": null, | |
| "top_p": null, | |
| "repetition_penalty": null, | |
| "num_beams": 1, | |
| "stream": false, | |
| "stop_words": [], | |
| "logprobs": false, | |
| "top_logprobs": null, | |
| "structured_outputs_regex": null, | |
| "adapters": [], | |
| "external_plugins": [], | |
| "custom_register_path": [], | |
| "model_kwargs": {}, | |
| "enable_npu_model_patch": true, | |
| "load_args": false, | |
| "load_data_args": false, | |
| "packing": false, | |
| "packing_length": null, | |
| "packing_num_proc": 1, | |
| "lazy_tokenize": true, | |
| "use_hf": true, | |
| "ignore_args_error": false, | |
| "use_swift_lora": false, | |
| "freeze_parameters": [ | |
| "model.visual", | |
| "model.visual.merger", | |
| "model.visual.deepstack_merger_list" | |
| ], | |
| "freeze_parameters_regex": null, | |
| "freeze_parameters_ratio": 0.0, | |
| "trainable_parameters": [], | |
| "trainable_parameters_regex": null, | |
| "freeze_llm": false, | |
| "freeze_vit": true, | |
| "freeze_aligner": true, | |
| "target_modules": [ | |
| "all-linear" | |
| ], | |
| "target_regex": null, | |
| "target_parameters": null, | |
| "modules_to_save": [], | |
| "lora_rank": 8, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05, | |
| "lora_bias": "none", | |
| "lora_dtype": null, | |
| "lorap_lr_ratio": null, | |
| "use_rslora": false, | |
| "use_dora": false, | |
| "lora_ga_batch_size": 2, | |
| "lora_ga_iters": 2, | |
| "lora_ga_max_length": 1024, | |
| "lora_ga_direction": "ArB2r", | |
| "lora_ga_scale": "stable", | |
| "lora_ga_stable_gamma": 16, | |
| "init_weights": true, | |
| "fourier_n_frequency": 2000, | |
| "fourier_scaling": 300.0, | |
| "boft_block_size": 4, | |
| "boft_block_num": 0, | |
| "boft_n_butterfly_factor": 1, | |
| "boft_dropout": 0.0, | |
| "vera_rank": 256, | |
| "vera_projection_prng_key": 0, | |
| "vera_dropout": 0.0, | |
| "vera_d_initial": 0.1, | |
| "adapter_act": "gelu", | |
| "adapter_length": 128, | |
| "adalora_target_r": 8, | |
| "adalora_init_r": 12, | |
| "adalora_tinit": 0, | |
| "adalora_tfinal": 0, | |
| "adalora_deltaT": 1, | |
| "adalora_beta1": 0.85, | |
| "adalora_beta2": 0.85, | |
| "adalora_orth_reg_weight": 0.5, | |
| "llamapro_num_new_blocks": 4, | |
| "llamapro_num_groups": null, | |
| "reft_layer_key": null, | |
| "reft_layers": null, | |
| "reft_rank": 4, | |
| "reft_intervention_type": "LoreftIntervention", | |
| "reft_args": null, | |
| "swanlab_token": null, | |
| "swanlab_project": "ms-swift", | |
| "swanlab_workspace": null, | |
| "swanlab_exp_name": null, | |
| "swanlab_notification_method": null, | |
| "swanlab_webhook_url": null, | |
| "swanlab_secret": null, | |
| "swanlab_sender_email": null, | |
| "swanlab_receiver_email": null, | |
| "swanlab_smtp_server": null, | |
| "swanlab_smtp_port": null, | |
| "swanlab_email_language": "zh", | |
| "swanlab_mode": "cloud", | |
| "add_version": true, | |
| "create_checkpoint_symlink": false, | |
| "zero_hpz_partition_size": null, | |
| "deepspeed_autotp_size": null, | |
| "swift_version": "4.3.0.dev0", | |
| "ckpt_dir": null, | |
| "rank": 0, | |
| "global_world_size": 8, | |
| "local_world_size": 8, | |
| "model_suffix": "Qwen3-VL-8B-Instruct", | |
| "template_meta": "QwenTemplateMeta(template_type='qwen3_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3VLTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='<think>\\n', non_thinking_prefix='', history_thinking_prefix='')", | |
| "_val_dataset_exists": true, | |
| "hub": "<class 'swift.hub.hub.HFHub'>", | |
| "evaluation_strategy": "no" | |
| } |