Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+acc_vs_latency_qwen-2.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,88 @@
+Disclaimer: IMPORTANT: This Apple Machine Learning Research Model is
+specifically developed and released by Apple Inc. ("Apple") for the sole purpose
+of scientific research of artificial intelligence and machine-learning
+technology. “Apple Machine Learning Research Model” means the model, including
+but not limited to algorithms, formulas, trained model weights, parameters,
+configurations, checkpoints, and any related materials (including
+documentation).
+
+This Apple Machine Learning Research Model is provided to You by
+Apple in consideration of your agreement to the following terms, and your use,
+modification, creation of Model Derivatives, and or redistribution of the Apple
+Machine Learning Research Model constitutes acceptance of this Agreement. If You
+do not agree with these terms, please do not use, modify, create Model
+Derivatives of, or distribute this Apple Machine Learning Research Model or
+Model Derivatives.
+
+* License Scope: In consideration of your agreement to abide by the following
+  terms, and subject to these terms, Apple hereby grants you a personal,
+  non-exclusive, worldwide, non-transferable, royalty-free, revocable, and
+  limited license, to use, copy, modify, distribute, and create Model
+  Derivatives (defined below) of the Apple Machine Learning Research Model
+  exclusively for Research Purposes. You agree that any Model Derivatives You
+  may create or that may be created for You will be limited to Research Purposes
+  as well. “Research Purposes” means non-commercial scientific research and
+  academic development activities, such as experimentation, analysis, testing
+  conducted by You with the sole intent to advance scientific knowledge and
+  research. “Research Purposes” does not include any commercial exploitation,
+  product development or use in any commercial product or service.
+
+* Distribution of Apple Machine Learning Research Model and Model Derivatives:
+  If you choose to redistribute Apple Machine Learning Research Model or its
+  Model Derivatives, you must provide a copy of this Agreement to such third
+  party, and ensure that the following attribution notice be provided: “Apple
+  Machine Learning Research Model is licensed under the Apple Machine Learning
+  Research Model License Agreement.” Additionally, all Model Derivatives must
+  clearly be identified as such, including disclosure of modifications and
+  changes made to the Apple Machine Learning Research Model. The name,
+  trademarks, service marks or logos of Apple may not be used to endorse or
+  promote Model Derivatives or the relationship between You and Apple. “Model
+  Derivatives” means any models or any other artifacts created by modifications,
+  improvements, adaptations, alterations to the architecture, algorithm or
+  training processes of the Apple Machine Learning Research Model, or by any
+  retraining, fine-tuning of the Apple Machine Learning Research Model.
+
+* No Other License: Except as expressly stated in this notice, no other rights
+  or licenses, express or implied, are granted by Apple herein, including but
+  not limited to any patent, trademark, and similar intellectual property rights
+  worldwide that may be infringed by the Apple Machine Learning Research Model,
+  the Model Derivatives or by other works in which the Apple Machine Learning
+  Research Model may be incorporated.
+
+* Compliance with Laws: Your use of Apple Machine Learning Research Model must
+  be in compliance with all applicable laws and regulations.
+
+* Term and Termination: The term of this Agreement will begin upon your
+  acceptance of this Agreement or use of the Apple Machine Learning Research
+  Model and will continue until terminated in accordance with the following
+  terms. Apple may terminate this Agreement at any time if You are in breach of
+  any term or condition of this Agreement. Upon termination of this Agreement,
+  You must cease to use all Apple Machine Learning Research Models and Model
+  Derivatives and permanently delete any copy thereof. Sections 3, 6 and 7 will
+  survive termination.
+
+* Disclaimer and Limitation of Liability: This Apple Machine Learning Research
+  Model and any outputs generated by the Apple Machine Learning Research Model
+  are provided on an “AS IS” basis. APPLE MAKES NO WARRANTIES, EXPRESS OR
+  IMPLIED, INCLUDING WITHOUT LIMITATION THE IMPLIED WARRANTIES OF
+  NON-INFRINGEMENT, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE,
+  REGARDING THE APPLE MACHINE LEARNING RESEARCH MODEL OR OUTPUTS GENERATED BY
+  THE APPLE MACHINE LEARNING RESEARCH MODEL. You are solely responsible for
+  determining the appropriateness of using or redistributing the Apple Machine
+  Learning Research Model and any outputs of the Apple Machine Learning Research
+  Model and assume any risks associated with Your use of the Apple Machine
+  Learning Research Model and any output and results. IN NO EVENT SHALL APPLE BE
+  LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+  IN ANY WAY OUT OF THE USE, REPRODUCTION, MODIFICATION AND/OR DISTRIBUTION OF
+  THE APPLE MACHINE LEARNING RESEARCH MODEL AND ANY OUTPUTS OF THE APPLE MACHINE
+  LEARNING RESEARCH MODEL, HOWEVER CAUSED AND WHETHER UNDER THEORY OF CONTRACT,
+  TORT (INCLUDING NEGLIGENCE), STRICT LIABILITY OR OTHERWISE, EVEN IF APPLE HAS
+  BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+* Governing Law: This Agreement will be governed by and construed under the laws
+  of the State of California without regard to its choice of law principles. The
+  Convention on Contracts for the International Sale of Goods shall not apply to
+  the Agreement except that the arbitration clause and any arbitration hereunder
+  shall be governed by the Federal Arbitration Act, Chapters 1 and 2. 
+
+Copyright (C) 2025 Apple Inc. All Rights Reserved.

README.md

@@ -0,0 +1,53 @@
+---
+license: apple-amlr
+license_name: apple-ascl
+license_link: https://github.com/apple/ml-fastvlm/blob/main/LICENSE_MODEL
+library_name: ml-fastvlm
+---
+# FastVLM: Efficient Vision Encoding for Vision Language Models
+
+FastVLM was introduced in
+**[FastVLM: Efficient Vision Encoding for Vision Language Models](https://www.arxiv.org/abs/2412.13303). (CVPR 2025)**
+
+[//]: # (![FastViTHD Performance](acc_vs_latency_qwen-2.png))
+<p align="center">
+<img src="acc_vs_latency_qwen-2.png" alt="Accuracy vs latency figure." width="400"/>
+</p>
+
+### Highlights
+* We introduce FastViTHD, a novel hybrid vision encoder designed to output fewer tokens and significantly reduce encoding time for high-resolution images.  
+* Our smallest variant outperforms LLaVA-OneVision-0.5B with 85x faster Time-to-First-Token (TTFT) and 3.4x smaller vision encoder.
+* Our larger variants using Qwen2-7B LLM outperform recent works like Cambrian-1-8B while using a single image encoder with a 7.9x faster TTFT.
+
+
+### Evaluations
+| Benchmark     | FastVLM-0.5B | FastVLM-1.5B | FastVLM-7B |
+|:--------------|:------------:|:------------:|:----------:|
+| Ai2D          |     68.0     |     77.4     |    83.6    |
+| ScienceQA     |     85.2     |     94.4     |    96.7    |
+| MMMU          |     33.9     |     37.8     |    45.4    |
+| VQAv2         |     76.3     |     79.1     |    80.8    |
+| ChartQA       |     76.0     |     80.1     |    85.0    |
+| TextVQA       |     64.5     |     70.4     |    74.9    |
+| InfoVQA       |     46.4     |     59.7     |    75.8    |
+| DocVQA        |     82.5     |     88.3     |    93.2    |
+| OCRBench      |     63.9     |     70.2     |    73.1    |
+| RealWorldQA   |     56.1     |     61.2     |    67.2    |
+| SeedBench-Img |     71.0     |     74.2     |    75.4    |
+
+
+### Usage Example
+The model has been exported to run with MLX. Follow the instructions in the official repository to use it in an iOS or macOS app.
+
+
+## Citation
+If you found this model useful, please cite the following paper:
+```
+@InProceedings{fastvlm2025,
+  author = {Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokul Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pouransari},
+  title = {FastVLM: Efficient Vision Encoding for Vision Language Models},
+  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  month = {June},
+  year = {2025},
+}
+```

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<image>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,45 @@
+{
+    "architectures": [
+        "LlavaQwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "freeze_mm_mlp_adapter": false,
+    "hidden_act": "silu",
+    "hidden_size": 896,
+    "image_aspect_ratio": "pad",
+    "image_grid_pinpoints": null,
+    "image_token_index": 151646,
+    "initializer_range": 0.02,
+    "intermediate_size": 4864,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 24,
+    "mm_hidden_size": 3072,
+    "mm_patch_merge_type": "flat",
+    "mm_projector_lr": null,
+    "mm_projector_type": "mlp2x_gelu",
+    "mm_use_im_patch_token": false,
+    "mm_use_im_start_end": false,
+    "mm_vision_select_feature": "patch",
+    "mm_vision_select_layer": -2,
+    "mm_vision_tower": "mobileclip_l_1024",
+    "model_type": "llava_qwen2",
+    "num_attention_heads": 14,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": false,
+    "tokenizer_model_max_length": 8192,
+    "tokenizer_padding_side": "right",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.3",
+    "tune_mm_mlp_adapter": false,
+    "unfreeze_mm_vision_tower": true,
+    "use_cache": true,
+    "use_mm_proj": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

fastvithd.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef95cee6af9141959f98a97b980e33f447ff4de8c843668b6f59df02234f0f79
+size 323561

fastvithd.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e6965421581f48f5500f46d9675b9b9c8e2dbb2870db790692c1a16b643e25
+size 490786624

fastvithd.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "058450D8-38E9-41BE-B9B5-C9865F6984F3": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "4F4061A4-280A-40BB-9A01-B08235063C4E": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "4F4061A4-280A-40BB-9A01-B08235063C4E"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29487bc0a004bb7611eb1368822b648699ff378e4d986521319e23929fbd7854
+size 1267485970

model.safetensors.index.json

@@ -0,0 +1,302 @@
+{
+    "metadata": {
+        "total_size": 1267449088
+    },
+    "weight_map": {
+        "language_model.lm_head.weight": "model.safetensors",
+        "language_model.model.embed_tokens.weight": "model.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.norm.weight": "model.safetensors",
+        "multi_modal_projector.linear_0.bias": "model.safetensors",
+        "multi_modal_projector.linear_0.weight": "model.safetensors",
+        "multi_modal_projector.linear_2.bias": "model.safetensors",
+        "multi_modal_projector.linear_2.weight": "model.safetensors"
+    }
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 1024,
+    "width": 1024
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 1024
+  }
+}

processor_config.json

@@ -0,0 +1,7 @@
+{
+  "image_token": "<image>",
+  "num_additional_image_tokens": 0,
+  "patch_size": 64,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": null
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb55926dbf36523cd143a5805102a9a516df89f7010313d182e1e710d94fb15
+size 11413284

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "only_llm": true,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}