Upload 43 files (#1)

- Upload 43 files (236ae1f25afd559e6b8684311b00388e4b3e7d7f)


Co-authored-by: Luke <Mizukiluke@users.noreply.huggingface.co>

README.md

@@ -0,0 +1,52 @@
+---
+tasks:
+
+- multimodal-dialogue
+
+studios:
+
+- damo/mPLUG-Owl
+
+model-type:
+
+- mplug-owl2
+
+domain:
+
+- multi-modal
+
+frameworks:
+
+- pytorch
+
+backbone:
+
+- transformer
+
+containers:
+
+license: apache-2.0
+
+language: 
+
+- en
+
+tags:
+
+- transformer
+- mPLUG
+- Multimodal
+- ChatGPT
+- GPT
+- Alibaba
+
+---
+
+# mPLUG-Owl2介绍
+
+mPLUG-Owl2是一种面向多模态语言模型的模块化的训练范式。其能学习与语言空间相适应的视觉知识，并支持在多模态场景(支持图片、文本输入)下进行多轮对话。它涌现多图关系理解，场景文本理解和基于视觉的文档理解等能力。
+
+## 模型描述
+
+mPLUG-Owl2基于mPLUG-2模块化的思想，通过多阶段分别训练模型的视觉底座与语言模型，使其视觉知识能与预训练语言模型紧密协作，达到了显著优于主流多模态语言模型的效果。
+![Training paradigm and model overview](assets/mplug_owl2_radar.png)

config.json

@@ -0,0 +1,176 @@
+{
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "mplug_owl2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "visual_config": {
+    "visual_abstractor": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_probs_dropout_prob": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_hidden_size": 1024,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "grid_size": 32,
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 2816,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "mplug_owl_visual_abstract",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 6,
+      "num_learnable_queries": 64,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.28.1",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "visual_model": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "quick_gelu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 448,
+      "initializer_factor": 1.0,
+      "initializer_range": 0.02,
+      "intermediate_size": 4096,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "mplug_owl_vision_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_hidden_layers": 24,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "projection_dim": 768,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.28.1",
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_flash_attn": false
+    }
+  },
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"multimodal-dialogue"}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
+}

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 448,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 448
+}
+

pytorch_model-1-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eda171a965e0f4f98941f0a45b2322d9f046f687205d0242fa6f45eefad04bc
+size 471896315

pytorch_model-10-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963430967add27b3cd84b55cc5d52a11fa1676450c790be813044fc59c43c3c5
+size 471896315

pytorch_model-11-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:182c23f36504e850c910a373a01372c52f0151f461e531d24a2b6e33a5b0b05a
+size 471896315

pytorch_model-12-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7abefa632c598f0eff7dc0b0bcba31debdd02850f65afc775e1b35b2b756004f
+size 471896315

pytorch_model-13-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbb00fc9a0375bd56e3817c25f950c1fbb9fd37da340e6a1e9ae19d856cdb34
+size 471896315

pytorch_model-14-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abf014e4e312136130bedfb0a77a623df76809dce37602ac072e655db353672
+size 471896315

pytorch_model-15-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c843bda69c0324a1ea56b41b99098a358c4925e9211847a446a29d52d95196cf
+size 471896315

pytorch_model-16-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32afd10b95a8f5871a6f9adc420772fb4288eec8cab80811b90e553aa08a1096
+size 471896315

pytorch_model-17-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bcfbf9937a670b675f2a3cade55d4c23b1ee6342c2e330a4f107c882db0fe8
+size 471896315

pytorch_model-18-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220b47b918bca9b929fda0598d941101efba77c2be23d6f694b5369c12d7ad5e
+size 471896315

pytorch_model-19-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f4d830c36a82131725760e5a8e1535cbdba217aeb5ed1ff5dab801ece4bd6c
+size 471896315

pytorch_model-2-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ebd22419c925cd4528d3182fa976694da76116d2896399f392134a4ffc4f60
+size 471896315

pytorch_model-20-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf47d1d758293babcb2cfd6242c1ff3fa179bc1e27f93efb83a4f1ed285886f3
+size 471896315

pytorch_model-21-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ecdc86f5b55942bd703518a82edc1b99b146e797cb911e6e1b9f392731a32a7
+size 471896315

pytorch_model-22-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b61398968246dad32f9a79729bb8b17ff7fbbc54df6df06d5a9c4a767f12e0
+size 471896315

pytorch_model-23-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94014e3c353d9e3a52afd6a9009a63fcfc9445545ca36ee73c3dfd69c024a3f4
+size 471896315

pytorch_model-24-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73c4c64ab429f85e92f2bf03f28c7450e56823bcdf5f3596ba4fcf63c86bd96
+size 471896315

pytorch_model-25-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05ec589fe7d22e270b7a11fd18974610a65db598aee16633a9f16a156b26701
+size 471896315

pytorch_model-26-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0053e94bfb2a49d60b9b6af5e3337df017cc284a8d3f3c3c724ac972dc42a92
+size 471896315

pytorch_model-27-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d49791d532ca66d65002aaa0aa0f7fc52708ee28503804d845ffeb77c7842b
+size 471896315

pytorch_model-28-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306cb650c62110e8b2e170659280c8d37569141611fa8ea69fe0c504bcac69c0
+size 471896315

pytorch_model-29-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51abf23024b4b6d219cbeb907a314faf4de60700936d7a879943d537335c9131
+size 471896315

pytorch_model-3-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d4c4fbb39a54e3a8bf79643ab7e74b80231c3f52504421ff8bca44dc9abb36
+size 471896315

pytorch_model-30-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2bccfdf1a1771248aef72d1f99babedfe6ef37a04a12787d08ef4318940c11
+size 471896315

pytorch_model-31-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c897a84a550da60e6ab2315b9c62e7faaa0e762b8d29ecfb567d9d81c2b439
+size 471896315

pytorch_model-32-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ad53e6f4961533b809a24e834496218c9b94d06c106b2799fcf4fe0d749f58
+size 471896315

pytorch_model-33-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5d2ac6af938bedd67cd5c53ef78a9d32401971e96d88ebf81168af56828258
+size 1295321821

pytorch_model-4-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4bfa35eb4a736c02e3d82d6e265b6eceebdaf012b81d02c64bcd2077e54bd4
+size 471896315

pytorch_model-5-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26905a37688e3a1676f9a0f45ed325042691a336cc46cc0fd3c5e4aadfe62cc
+size 471896315

pytorch_model-6-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67857b8c240e5a4e6b6486f1ef86b8b86d48c014d39020a9364761bc286ddbbd
+size 471896315

pytorch_model-7-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74098fe2053bbce4507160f4549cfde263c42246b9b15f87a2535e4f3979fd4
+size 471896315

pytorch_model-8-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256484eef34f0326ca6af84922a66e1106a184da183d9a2b8ccf122f16009b8f
+size 471896315

pytorch_model-9-of-33.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c1424bc245b2882cb8d4f8cc33d8b13ee4619b08d0a5b004911f1a42432778
+size 471896315

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"model.layers.0.self_attn.q_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-1-of-33.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-2-of-33.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-3-of-33.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-4-of-33.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-5-of-33.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-6-of-33.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-7-of-33.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-8-of-33.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-9-of-33.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-10-of-33.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-11-of-33.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-12-of-33.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-13-of-33.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-14-of-33.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-15-of-33.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-16-of-33.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-17-of-33.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-18-of-33.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-19-of-33.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-20-of-33.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-21-of-33.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-22-of-33.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-23-of-33.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-24-of-33.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-25-of-33.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-26-of-33.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-27-of-33.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-28-of-33.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-29-of-33.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-30-of-33.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-31-of-33.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-32-of-33.bin", "model.embed_tokens.weight": "pytorch_model-33-of-33.bin", "model.norm.weight": "pytorch_model-33-of-33.bin", "lm_head.weight": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.cls_token": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.patch_embed.weight": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.position_embedding": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.post_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.post_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.query_embeds": "pytorch_model-33-of-33.bin", "model.visual_abstractor.visual_fc.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.visual_fc.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.vit_eos": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin"}, "metadata": {"total_size": 16395722752}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}