Upload folder using huggingface_hub

.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 +1,151 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.6.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "32.mlp.gate_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.26.mlp.down_proj",
+    "layers.12.mlp.down_proj",
+    "layers.19.mlp.down_proj",
+    "layers.31.mlp.gate_proj",
+    "layers.12.mlp.gate_proj",
+    "k_proj",
+    "layers.13.mlp.down_proj",
+    "layers.24.mlp.gate_proj",
+    "layers.10.mlp.down_proj",
+    "layers.29.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.2.mlp.gate_proj",
+    "34.mlp.up_proj",
+    "layers.23.mlp.gate_proj",
+    "layers.28.mlp.gate_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.0.mlp.up_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.18.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "layers.30.mlp.up_proj",
+    "layers.9.mlp.up_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.14.mlp.up_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.29.mlp.down_proj",
+    "layers.28.mlp.down_proj",
+    "layers.20.mlp.gate_proj",
+    "34.mlp.gate_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.4.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.1.mlp.up_proj",
+    "layers.2.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.2.mlp.down_proj",
+    "layers.5.mlp.up_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.27.mlp.gate_proj",
+    "33.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "layers.17.mlp.up_proj",
+    "layers.31.mlp.down_proj",
+    "layers.11.mlp.down_proj",
+    "35.mlp.down_proj",
+    "layers.27.mlp.up_proj",
+    "layers.28.mlp.up_proj",
+    "q_proj",
+    "layers.16.mlp.gate_proj",
+    "layers.25.mlp.down_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.18.mlp.down_proj",
+    "layers.24.mlp.up_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.16.mlp.down_proj",
+    "layers.16.mlp.up_proj",
+    "layers.30.mlp.gate_proj",
+    "32.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.21.mlp.up_proj",
+    "33.mlp.gate_proj",
+    "layers.26.mlp.gate_proj",
+    "35.mlp.up_proj",
+    "layers.29.mlp.gate_proj",
+    "layers.21.mlp.down_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.14.mlp.down_proj",
+    "layers.26.mlp.up_proj",
+    "layers.20.mlp.up_proj",
+    "layers.7.mlp.up_proj",
+    "layers.17.mlp.down_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.3.mlp.down_proj",
+    "layers.13.mlp.up_proj",
+    "layers.20.mlp.down_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.23.mlp.down_proj",
+    "layers.15.mlp.up_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.23.mlp.up_proj",
+    "32.mlp.up_proj",
+    "layers.0.mlp.down_proj",
+    "o_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.22.mlp.down_proj",
+    "v_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.5.mlp.down_proj",
+    "layers.7.mlp.down_proj",
+    "layers.22.mlp.up_proj",
+    "layers.9.mlp.gate_proj",
+    "34.mlp.down_proj",
+    "layers.1.mlp.down_proj",
+    "35.mlp.gate_proj",
+    "layers.9.mlp.down_proj",
+    "layers.30.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "layers.11.mlp.up_proj",
+    "layers.3.mlp.up_proj",
+    "layers.6.mlp.up_proj",
+    "layers.8.mlp.up_proj",
+    "layers.31.mlp.up_proj",
+    "33.mlp.up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238a1299db9f38eb78555655924772e84efe183447eafd03ed42144f48786bbf
+size 1915817456

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}