From a039e999a3914848e014bae0aab2689ba9510159 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 8 Jun 2026 19:09:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: iic/GUI-Owl-7B Source: Original Platform --- .gitattributes | 51 +++ README.md | 94 ++++ chat_template.json | 3 + config.json | 61 +++ configuration.json | 1 + generation_config.json | 14 + merges.txt | 3 + model-00001-of-00005.safetensors | 3 + model-00002-of-00005.safetensors | 3 + model-00003-of-00005.safetensors | 3 + model-00004-of-00005.safetensors | 3 + model-00005-of-00005.safetensors | 3 + model.safetensors.index.json | 736 +++++++++++++++++++++++++++++++ preprocessor_config.json | 19 + tokenizer.json | 3 + tokenizer_config.json | 239 ++++++++++ vocab.json | 3 + 17 files changed, 1242 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.json create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model-00001-of-00005.safetensors create mode 100644 model-00002-of-00005.safetensors create mode 100644 model-00003-of-00005.safetensors create mode 100644 model-00004-of-00005.safetensors create mode 100644 model-00005-of-00005.safetensors create mode 100644 model.safetensors.index.json create mode 100644 preprocessor_config.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d2fc868 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..a326861 --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +license: mit +language: +- en +base_model: +- Qwen/Qwen2.5-VL-7B-Instruct +tags: +- arxiv:2508.15144 +--- + +# GUI-Owl + +
+ +
+ +GUI-Owl is a model series developed as part of the Mobile-Agent-V3 project. It achieves state-of-the-art performance across a range of GUI automation benchmarks, including ScreenSpot-V2, ScreenSpot-Pro, OSWorld-G, MMBench-GUI, Android Control, Android World, and OSWorld. Furthermore, it can be instantiated as various specialized agents within the Mobile-Agent-V3 multi-agent framework to accomplish more complex tasks. + +* **Paper**: [Paper Link](https://github.com/X-PLUG/MobileAgent/blob/main/Mobile-Agent-v3/assets/MobileAgentV3_Tech.pdf) +* **GitHub Repository**: https://github.com/X-PLUG/MobileAgent +* **Online Demo**: Comming soon + +## Performance + +### ScreenSpot-V2, ScreenSpot-Pro and OSWorld-G + + + + +### MMBench-GUI L1, L2 and Android Control + + + + +### Android World and OSWorld-Verified + + +## Usage + +Please refer to our cookbook. + +## Deploy + +We recommand deploy GUI-Owl-7B through vllm + +This script has been validated on an A100 with 96 GB of VRAM. +```bash +PIXEL_ARGS='{"min_pixels":3136,"max_pixels":10035200}' +IMAGE_LIMIT_ARGS='image=2' +MP_SIZE=1 +MM_KWARGS=( + --mm-processor-kwargs $PIXEL_ARGS + --limit-mm-per-prompt $IMAGE_LIMIT_ARGS +) + +vllm serve $CKPT \ + --max-model-len 32768 ${MM_KWARGS[@]} \ + --tensor-parallel-size $MP_SIZE \ + --allowed-local-media-path '/' \ + --port 4243 +``` + +If you want GUI-Owl to recieve more than two images, you could increase `IMAGE_LIMIT_ARGS` and reduce `max_pixels`. + +For example: +```bash +PIXEL_ARGS='{"min_pixels":3136,"max_pixels":3211264}' +IMAGE_LIMIT_ARGS='image=5' +MP_SIZE=1 +MM_KWARGS=( + --mm-processor-kwargs $PIXEL_ARGS + --limit-mm-per-prompt $IMAGE_LIMIT_ARGS +) + +vllm serve $CKPT \ + --max-model-len 32768 ${MM_KWARGS[@]} \ + --tensor-parallel-size $MP_SIZE \ + --allowed-local-media-path '/' \ + --port 4243 +``` + +## Citation +If you find our paper and model useful in your research, feel free to give us a cite. +``` +@misc{ye2025mobileagentv3foundamentalagentsgui, + title={Mobile-Agent-v3: Foundamental Agents for GUI Automation}, + author={Jiabo Ye and Xi Zhang and Haiyang Xu and Haowei Liu and Junyang Wang and Zhaoqing Zhu and Ziwei Zheng and Feiyu Gao and Junjie Cao and Zhengxi Lu and Jitong Liao and Qi Zheng and Fei Huang and Jingren Zhou and Ming Yan}, + year={2025}, + eprint={2508.15144}, + archivePrefix={arXiv}, + primaryClass={cs.AI}, + url={https://arxiv.org/abs/2508.15144}, +} +``` diff --git a/chat_template.json b/chat_template.json new file mode 100644 index 0000000..732bd68 --- /dev/null +++ b/chat_template.json @@ -0,0 +1,3 @@ +{ + "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}" +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..04e0a00 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "vision_start_token_id": 151652, + "vision_end_token_id": 151653, + "vision_token_id": 151654, + "image_token_id": 151655, + "video_token_id": 151656, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2_5_vl", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.41.2", + "use_cache": true, + "use_sliding_window": false, + "vision_config": { + "depth": 32, + "hidden_act": "silu", + "hidden_size": 1280, + "intermediate_size": 3456, + "num_heads": 16, + "in_chans": 3, + "out_hidden_size": 3584, + "patch_size": 14, + "spatial_merge_size": 2, + "spatial_patch_size": 14, + "window_size": 112, + "fullatt_block_indexes": [ + 7, + 15, + 23, + 31 + ], + "tokens_per_second": 2, + "temporal_patch_size": 2 + }, + "rope_scaling": { + "type": "mrope", + "mrope_section": [ + 16, + 24, + 24 + ] + }, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..3a6d425 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"image-text-to-text"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..545039a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "pad_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "repetition_penalty": 1.05, + "temperature": 0.1, + "top_p": 0.001, + "top_k": 1, + "transformers_version": "4.37.0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..7ce1d95 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3 +size 1671839 diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..5eda588 --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99a533673e568eae50469171b7fcc82f4944bbabc9a292a436e008750ac878ce +size 3909085224 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..075ac4c --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa19068d582aba36d8436ffdaa4509164bce6fa5979a75a569820851430f558 +size 3864726320 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..8b56f27 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6519b7723cdecbcd0d663c0dc67d6c12e9320b6ea0db461113722dabecdfe664 +size 3864726424 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..83a3632 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4fee59620c50ef9c2e91ea520daebd9b17c2dbed5950c4f446d0df5232980e +size 3864733680 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..c4deb59 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac8bdc3f1f15f29936008e12648ce2d17b300d7a82376ae7511b85054e7003b1 +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6a55857 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,736 @@ +{ + "metadata": { + "total_size": 16593185280 + }, + "weight_map": { + "lm_head.weight": "model-00005-of-00005.safetensors", + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.norm.weight": "model-00004-of-00005.safetensors", + "visual.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.24.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.24.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.25.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.25.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.26.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.26.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.27.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.27.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.27.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.27.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.27.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.27.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.28.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.28.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.28.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.28.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.28.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.28.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.29.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.29.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.29.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.29.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.29.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.29.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.30.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.30.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.30.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.30.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.30.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.30.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.31.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.31.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.31.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.31.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.31.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.31.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors", + "visual.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors", + "visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors", + "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00005.safetensors", + "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors", + "visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors", + "visual.merger.ln_q.weight": "model-00001-of-00005.safetensors", + "visual.merger.mlp.0.bias": "model-00001-of-00005.safetensors", + "visual.merger.mlp.0.weight": "model-00001-of-00005.safetensors", + "visual.merger.mlp.2.bias": "model-00001-of-00005.safetensors", + "visual.merger.mlp.2.weight": "model-00001-of-00005.safetensors", + "visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..7f3b746 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,19 @@ +{ + "min_pixels": 3136, + "max_pixels": 12845056, + "patch_size": 14, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "processor_class": "Qwen2_5_VLProcessor" +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd01866 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19564a48c4f71a2a1b937cce34c737a1e662b171c5f5d7edf641a15cd896f07d +size 7032399 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..f10efca --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,239 @@ +{ + "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": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- '\\n' }}\n {{- '{\"type\": \"function\", \"function\": {\"name\": \"' }}\n {{- tool.name }}\n {{- '\"' }}\n {%- for key, value in tool.items() %}\n {%- if key != 'name' %}\n {{- ', \"' }}\n {{- key }}\n {{- '\": ' }}\n {{- value|tojson}}\n {%- endif %}\n {%- endfor %}\n {{- '}}' }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in message.content %}\n {%- set content = message.content.split('')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments }}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "add_bos_token": false +} \ No newline at end of file diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833