Upload 10 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/modelscope/hub/models/google/paligemma-3b-pt-224",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(model.language_model.*\\.(o_proj|gate_proj|v_proj|k_proj|q_proj|up_proj|down_proj))$",
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab71f0528599ecf86504e36a4d8b32311b61962e897ac3148f94f3c0ce0dc67c
+size 78483848

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 257152
+}

additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

args.json

@@ -0,0 +1,119 @@
+{
+  "model": "google/paligemma-3b-pt-224",
+  "model_type": "paligemma",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "float16",
+  "attn_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": "paligemma",
+  "system": null,
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "data_seed": 42,
+  "dataset_num_proc": 1,
+  "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,
+  "remove_unused_columns": true,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": "bnb",
+  "quant_bits": 4,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "float16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": "/kaggle/working/output_Kvasir-VQA-x1/v0-20250902-124816/checkpoint-188",
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "lora",
+  "adapters": [
+    "/kaggle/working/output_Kvasir-VQA-x1/v0-20250902-124816/checkpoint-188"
+  ],
+  "external_plugins": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": true,
+  "load_data_args": false,
+  "packing": false,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": true,
+  "hub_token": null,
+  "ddp_timeout": 18000000,
+  "ddp_backend": null,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "merge_lora": false,
+  "safe_serialization": true,
+  "max_shard_size": "5GB",
+  "output_dir": "/kaggle/working/output_Kvasir-VQA-x1/v0-20250902-124816/checkpoint-188-bnb-int4",
+  "quant_n_samples": 256,
+  "quant_batch_size": 1,
+  "group_size": 128,
+  "to_cached_dataset": false,
+  "to_ollama": false,
+  "to_mcore": false,
+  "to_hf": false,
+  "mcore_model": null,
+  "mcore_adapters": [],
+  "thread_count": null,
+  "test_convert_precision": false,
+  "push_to_hub": true,
+  "hub_model_id": "Kvasir-VQA-x1-lora_250902-1244",
+  "hub_private_repo": false,
+  "commit_message": "update files",
+  "to_peft_format": false,
+  "exist_ok": false,
+  "rank": -1,
+  "local_rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "paligemma-3b-pt-224",
+  "model_info": "ModelInfo(model_type='paligemma', model_dir='/root/.cache/huggingface/hub/models--google--paligemma-3b-pt-224/snapshots/35e4f46485b4d07967e7e9935bc3786aad50687c', torch_dtype=torch.float16, max_model_len=8192, quant_method='bnb', quant_bits=4, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='paligemma', model_groups=[ModelGroup(models=[Model(ms_model_id='AI-ModelScope/paligemma-3b-pt-224', hf_model_id='google/paligemma-3b-pt-224', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma-3b-pt-448', hf_model_id='google/paligemma-3b-pt-448', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma-3b-pt-896', hf_model_id='google/paligemma-3b-pt-896', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/paligemma-3b-mix-224', hf_model_id='google/paligemma-3b-mix-224', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma-3b-mix-448', hf_model_id='google/paligemma-3b-mix-448', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/paligemma2-3b-pt-224', hf_model_id='google/paligemma2-3b-pt-224', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-3b-pt-448', hf_model_id='google/paligemma2-3b-pt-448', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-3b-pt-896', hf_model_id='google/paligemma2-3b-pt-896', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-10b-pt-224', hf_model_id='google/paligemma2-10b-pt-224', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-10b-pt-448', hf_model_id='google/paligemma2-10b-pt-448', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-10b-pt-896', hf_model_id='google/paligemma2-10b-pt-896', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-28b-pt-224', hf_model_id='google/paligemma2-28b-pt-224', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-28b-pt-448', hf_model_id='google/paligemma2-28b-pt-448', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-28b-pt-896', hf_model_id='google/paligemma2-28b-pt-896', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/paligemma2-3b-ft-docci-448', hf_model_id='google/paligemma2-3b-ft-docci-448', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/paligemma2-10b-ft-docci-448', hf_model_id='google/paligemma2-10b-ft-docci-448', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='paligemma', get_function=<function get_model_tokenizer_paligemma_vision at 0x7a9427329a80>, model_arch=MultiModelKeys(arch_name='llava_hf', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.multi_modal_projector'], vision_tower=['model.vision_tower'], generator=[]), architectures=['PaliGemmaForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.41'], tags=['vision'])",
+  "model_dir": "/root/.cache/huggingface/hub/models--google--paligemma-3b-pt-224/snapshots/35e4f46485b4d07967e7e9935bc3786aad50687c",
+  "hub": "<class 'swift.hub.hub.HFHub'>"
+}

preprocessor_config.json

@@ -0,0 +1,40 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format",
+    "do_convert_rgb"
+  ],
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "PaliGemmaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172fab587d68c56b63eb3620057c62dfd15e503079ff7fce584692e3fd5bf4da
+size 34600820

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8986bb4f423f07f8c7f70d0dbe3526fb2316056c17bae71b1ea975e77a168fc6
+size 4264023