Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/hdfs/public/jirong/codebase/RoboICL/models/pretrained_vl",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 163419
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 1003520,
+  "merge_size": 1,
+  "min_pixels": 3136,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 1003520,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 1
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e8a5d2f7909b688daca5b58cc67527884111998cce4ebbf7ae69139173fbe9
+size 3122749946

special_tokens_map.json

@@ -0,0 +1,118 @@
+{
+  "additional_special_tokens": [
+    "<|frame_0|>",
+    "<|frame_1|>",
+    "<|frame_2|>",
+    "<|frame_3|>",
+    "<|frame_4|>",
+    "<|frame_5|>",
+    "<|frame_6|>",
+    "<|frame_7|>",
+    "<|frame_8|>",
+    "<|frame_9|>",
+    "<|frame_10|>",
+    "<|frame_11|>",
+    "<|frame_12|>",
+    "<|frame_13|>",
+    "<|frame_14|>",
+    "<|frame_15|>",
+    "<|frame_16|>",
+    "<|frame_17|>",
+    "<|frame_18|>",
+    "<|frame_19|>",
+    "<|frame_20|>",
+    "<|frame_21|>",
+    "<|frame_22|>",
+    "<|frame_23|>",
+    "<|frame_24|>",
+    "<|frame_25|>",
+    "<|frame_26|>",
+    "<|frame_27|>",
+    "<|frame_28|>",
+    "<|frame_29|>",
+    "<|frame_30|>",
+    "<|frame_31|>",
+    "<|frame_32|>",
+    "<|frame_33|>",
+    "<|frame_34|>",
+    "<|frame_35|>",
+    "<|frame_36|>",
+    "<|frame_37|>",
+    "<|frame_38|>",
+    "<|frame_39|>",
+    "<|frame_40|>",
+    "<|frame_41|>",
+    "<|frame_42|>",
+    "<|frame_43|>",
+    "<|frame_44|>",
+    "<|frame_45|>",
+    "<|frame_46|>",
+    "<|frame_47|>",
+    "<|frame_48|>",
+    "<|frame_49|>",
+    "<|frame_50|>",
+    "<|frame_51|>",
+    "<|frame_52|>",
+    "<|frame_53|>",
+    "<|frame_54|>",
+    "<|frame_55|>",
+    "<|frame_56|>",
+    "<|frame_57|>",
+    "<|frame_58|>",
+    "<|frame_59|>",
+    "<|frame_60|>",
+    "<|frame_61|>",
+    "<|frame_62|>",
+    "<|frame_63|>",
+    "<|frame_64|>",
+    "<|frame_65|>",
+    "<|frame_66|>",
+    "<|frame_67|>",
+    "<|frame_68|>",
+    "<|frame_69|>",
+    "<|frame_70|>",
+    "<|frame_71|>",
+    "<|frame_72|>",
+    "<|frame_73|>",
+    "<|frame_74|>",
+    "<|frame_75|>",
+    "<|frame_76|>",
+    "<|frame_77|>",
+    "<|frame_78|>",
+    "<|frame_79|>",
+    "<|frame_80|>",
+    "<|frame_81|>",
+    "<|frame_82|>",
+    "<|frame_83|>",
+    "<|frame_84|>",
+    "<|frame_85|>",
+    "<|frame_86|>",
+    "<|frame_87|>",
+    "<|frame_88|>",
+    "<|frame_89|>",
+    "<|frame_90|>",
+    "<|frame_91|>",
+    "<|frame_92|>",
+    "<|frame_93|>",
+    "<|frame_94|>",
+    "<|frame_95|>",
+    "<|frame_96|>",
+    "<|frame_97|>",
+    "<|frame_98|>",
+    "<|frame_99|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}