Add files using upload-large-folder tool

README.md

@@ -0,0 +1,37 @@
+---
+base_model:
+  - ByteDance-Seed/BAGEL-7B-MoT
+base_model_relation: quantized
+pipeline_tag: any-to-any
+tags:
+- dfloat11
+- df11
+- lossless compression
+- 70% size, 100% accuracy
+---
+
+# DFloat11 Compressed Model: `ByteDance-Seed/BAGEL-7B-MoT`
+
+This model uses **DFloat11** lossless compression. It's 32% smaller than the original BFloat16 model, yet produces bit-identical outputs and runs efficiently on GPUs.
+
+### 📊 Performance Comparison
+
+| Metric                             | Wan2.1-T2V-14B (BFloat16) | Wan2.1-T2V-14B (DFloat11) |
+| ---------------------------------- | ------------------------- | ------------------------- |
+| Model Size                         | 29.21 GB                  | 19.89 GB                  |
+| Peak GPU Memory<br>(1024x1024 image generation) | 30.07 GB                  | 21.76 GB                  |
+| Generation Time<br>(on an A100 GPU)   | 54 seconds               | 58 seconds               |
+
+### 🔍 How It Works
+
+We apply Huffman coding to the exponent bits of BFloat16 model weights, which are highly compressible. We leverage hardware-aware algorithmic designs to enable highly efficient, on-the-fly weight decompression directly on the GPU. Find out more in our [research paper](https://arxiv.org/abs/2504.11651).
+
+### 🔧 How to Use
+
+A complete usage guide is available in our GitHub repository (forked from the official Bagel repository): [https://github.com/LeanModels/Bagel-DFloat11](github.com/LeanModels/Bagel-DFloat11).
+
+### 📄 Learn More
+
+* **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
+* **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
+* **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)

config.json

@@ -0,0 +1,189 @@
+{
+  "dfloat11_config": {
+    "bytes_per_thread": 8,
+    "pattern_dict": {
+      "language_model\\.model\\.embed_tokens": [],
+      "language_model\\.model\\.layers.\\d+": [
+          "self_attn.q_proj",
+          "self_attn.k_proj",
+          "self_attn.v_proj",
+          "self_attn.o_proj",
+          "self_attn.q_proj_moe_gen",
+          "self_attn.k_proj_moe_gen",
+          "self_attn.v_proj_moe_gen",
+          "self_attn.o_proj_moe_gen",
+          "mlp.gate_proj",
+          "mlp.up_proj",
+          "mlp.down_proj",
+          "mlp_moe_gen.gate_proj",
+          "mlp_moe_gen.up_proj",
+          "mlp_moe_gen.down_proj"
+      ],
+      "language_model\\.lm_head": [],
+      "vit_model": [
+        "vision_model.encoder.layers.0.self_attn.k_proj",
+        "vision_model.encoder.layers.0.self_attn.v_proj",
+        "vision_model.encoder.layers.0.self_attn.q_proj",
+        "vision_model.encoder.layers.0.self_attn.out_proj",
+        "vision_model.encoder.layers.0.mlp.fc1",
+        "vision_model.encoder.layers.0.mlp.fc2",
+        "vision_model.encoder.layers.1.self_attn.k_proj",
+        "vision_model.encoder.layers.1.self_attn.v_proj",
+        "vision_model.encoder.layers.1.self_attn.q_proj",
+        "vision_model.encoder.layers.1.self_attn.out_proj",
+        "vision_model.encoder.layers.1.mlp.fc1",
+        "vision_model.encoder.layers.1.mlp.fc2",
+        "vision_model.encoder.layers.2.self_attn.k_proj",
+        "vision_model.encoder.layers.2.self_attn.v_proj",
+        "vision_model.encoder.layers.2.self_attn.q_proj",
+        "vision_model.encoder.layers.2.self_attn.out_proj",
+        "vision_model.encoder.layers.2.mlp.fc1",
+        "vision_model.encoder.layers.2.mlp.fc2",
+        "vision_model.encoder.layers.3.self_attn.k_proj",
+        "vision_model.encoder.layers.3.self_attn.v_proj",
+        "vision_model.encoder.layers.3.self_attn.q_proj",
+        "vision_model.encoder.layers.3.self_attn.out_proj",
+        "vision_model.encoder.layers.3.mlp.fc1",
+        "vision_model.encoder.layers.3.mlp.fc2",
+        "vision_model.encoder.layers.4.self_attn.k_proj",
+        "vision_model.encoder.layers.4.self_attn.v_proj",
+        "vision_model.encoder.layers.4.self_attn.q_proj",
+        "vision_model.encoder.layers.4.self_attn.out_proj",
+        "vision_model.encoder.layers.4.mlp.fc1",
+        "vision_model.encoder.layers.4.mlp.fc2",
+        "vision_model.encoder.layers.5.self_attn.k_proj",
+        "vision_model.encoder.layers.5.self_attn.v_proj",
+        "vision_model.encoder.layers.5.self_attn.q_proj",
+        "vision_model.encoder.layers.5.self_attn.out_proj",
+        "vision_model.encoder.layers.5.mlp.fc1",
+        "vision_model.encoder.layers.5.mlp.fc2",
+        "vision_model.encoder.layers.6.self_attn.k_proj",
+        "vision_model.encoder.layers.6.self_attn.v_proj",
+        "vision_model.encoder.layers.6.self_attn.q_proj",
+        "vision_model.encoder.layers.6.self_attn.out_proj",
+        "vision_model.encoder.layers.6.mlp.fc1",
+        "vision_model.encoder.layers.6.mlp.fc2",
+        "vision_model.encoder.layers.7.self_attn.k_proj",
+        "vision_model.encoder.layers.7.self_attn.v_proj",
+        "vision_model.encoder.layers.7.self_attn.q_proj",
+        "vision_model.encoder.layers.7.self_attn.out_proj",
+        "vision_model.encoder.layers.7.mlp.fc1",
+        "vision_model.encoder.layers.7.mlp.fc2",
+        "vision_model.encoder.layers.8.self_attn.k_proj",
+        "vision_model.encoder.layers.8.self_attn.v_proj",
+        "vision_model.encoder.layers.8.self_attn.q_proj",
+        "vision_model.encoder.layers.8.self_attn.out_proj",
+        "vision_model.encoder.layers.8.mlp.fc1",
+        "vision_model.encoder.layers.8.mlp.fc2",
+        "vision_model.encoder.layers.9.self_attn.k_proj",
+        "vision_model.encoder.layers.9.self_attn.v_proj",
+        "vision_model.encoder.layers.9.self_attn.q_proj",
+        "vision_model.encoder.layers.9.self_attn.out_proj",
+        "vision_model.encoder.layers.9.mlp.fc1",
+        "vision_model.encoder.layers.9.mlp.fc2",
+        "vision_model.encoder.layers.10.self_attn.k_proj",
+        "vision_model.encoder.layers.10.self_attn.v_proj",
+        "vision_model.encoder.layers.10.self_attn.q_proj",
+        "vision_model.encoder.layers.10.self_attn.out_proj",
+        "vision_model.encoder.layers.10.mlp.fc1",
+        "vision_model.encoder.layers.10.mlp.fc2",
+        "vision_model.encoder.layers.11.self_attn.k_proj",
+        "vision_model.encoder.layers.11.self_attn.v_proj",
+        "vision_model.encoder.layers.11.self_attn.q_proj",
+        "vision_model.encoder.layers.11.self_attn.out_proj",
+        "vision_model.encoder.layers.11.mlp.fc1",
+        "vision_model.encoder.layers.11.mlp.fc2",
+        "vision_model.encoder.layers.12.self_attn.k_proj",
+        "vision_model.encoder.layers.12.self_attn.v_proj",
+        "vision_model.encoder.layers.12.self_attn.q_proj",
+        "vision_model.encoder.layers.12.self_attn.out_proj",
+        "vision_model.encoder.layers.12.mlp.fc1",
+        "vision_model.encoder.layers.12.mlp.fc2",
+        "vision_model.encoder.layers.13.self_attn.k_proj",
+        "vision_model.encoder.layers.13.self_attn.v_proj",
+        "vision_model.encoder.layers.13.self_attn.q_proj",
+        "vision_model.encoder.layers.13.self_attn.out_proj",
+        "vision_model.encoder.layers.13.mlp.fc1",
+        "vision_model.encoder.layers.13.mlp.fc2",
+        "vision_model.encoder.layers.14.self_attn.k_proj",
+        "vision_model.encoder.layers.14.self_attn.v_proj",
+        "vision_model.encoder.layers.14.self_attn.q_proj",
+        "vision_model.encoder.layers.14.self_attn.out_proj",
+        "vision_model.encoder.layers.14.mlp.fc1",
+        "vision_model.encoder.layers.14.mlp.fc2",
+        "vision_model.encoder.layers.15.self_attn.k_proj",
+        "vision_model.encoder.layers.15.self_attn.v_proj",
+        "vision_model.encoder.layers.15.self_attn.q_proj",
+        "vision_model.encoder.layers.15.self_attn.out_proj",
+        "vision_model.encoder.layers.15.mlp.fc1",
+        "vision_model.encoder.layers.15.mlp.fc2",
+        "vision_model.encoder.layers.16.self_attn.k_proj",
+        "vision_model.encoder.layers.16.self_attn.v_proj",
+        "vision_model.encoder.layers.16.self_attn.q_proj",
+        "vision_model.encoder.layers.16.self_attn.out_proj",
+        "vision_model.encoder.layers.16.mlp.fc1",
+        "vision_model.encoder.layers.16.mlp.fc2",
+        "vision_model.encoder.layers.17.self_attn.k_proj",
+        "vision_model.encoder.layers.17.self_attn.v_proj",
+        "vision_model.encoder.layers.17.self_attn.q_proj",
+        "vision_model.encoder.layers.17.self_attn.out_proj",
+        "vision_model.encoder.layers.17.mlp.fc1",
+        "vision_model.encoder.layers.17.mlp.fc2",
+        "vision_model.encoder.layers.18.self_attn.k_proj",
+        "vision_model.encoder.layers.18.self_attn.v_proj",
+        "vision_model.encoder.layers.18.self_attn.q_proj",
+        "vision_model.encoder.layers.18.self_attn.out_proj",
+        "vision_model.encoder.layers.18.mlp.fc1",
+        "vision_model.encoder.layers.18.mlp.fc2",
+        "vision_model.encoder.layers.19.self_attn.k_proj",
+        "vision_model.encoder.layers.19.self_attn.v_proj",
+        "vision_model.encoder.layers.19.self_attn.q_proj",
+        "vision_model.encoder.layers.19.self_attn.out_proj",
+        "vision_model.encoder.layers.19.mlp.fc1",
+        "vision_model.encoder.layers.19.mlp.fc2",
+        "vision_model.encoder.layers.20.self_attn.k_proj",
+        "vision_model.encoder.layers.20.self_attn.v_proj",
+        "vision_model.encoder.layers.20.self_attn.q_proj",
+        "vision_model.encoder.layers.20.self_attn.out_proj",
+        "vision_model.encoder.layers.20.mlp.fc1",
+        "vision_model.encoder.layers.20.mlp.fc2",
+        "vision_model.encoder.layers.21.self_attn.k_proj",
+        "vision_model.encoder.layers.21.self_attn.v_proj",
+        "vision_model.encoder.layers.21.self_attn.q_proj",
+        "vision_model.encoder.layers.21.self_attn.out_proj",
+        "vision_model.encoder.layers.21.mlp.fc1",
+        "vision_model.encoder.layers.21.mlp.fc2",
+        "vision_model.encoder.layers.22.self_attn.k_proj",
+        "vision_model.encoder.layers.22.self_attn.v_proj",
+        "vision_model.encoder.layers.22.self_attn.q_proj",
+        "vision_model.encoder.layers.22.self_attn.out_proj",
+        "vision_model.encoder.layers.22.mlp.fc1",
+        "vision_model.encoder.layers.22.mlp.fc2",
+        "vision_model.encoder.layers.23.self_attn.k_proj",
+        "vision_model.encoder.layers.23.self_attn.v_proj",
+        "vision_model.encoder.layers.23.self_attn.q_proj",
+        "vision_model.encoder.layers.23.self_attn.out_proj",
+        "vision_model.encoder.layers.23.mlp.fc1",
+        "vision_model.encoder.layers.23.mlp.fc2",
+        "vision_model.encoder.layers.24.self_attn.k_proj",
+        "vision_model.encoder.layers.24.self_attn.v_proj",
+        "vision_model.encoder.layers.24.self_attn.q_proj",
+        "vision_model.encoder.layers.24.self_attn.out_proj",
+        "vision_model.encoder.layers.24.mlp.fc1",
+        "vision_model.encoder.layers.24.mlp.fc2",
+        "vision_model.encoder.layers.25.self_attn.k_proj",
+        "vision_model.encoder.layers.25.self_attn.v_proj",
+        "vision_model.encoder.layers.25.self_attn.q_proj",
+        "vision_model.encoder.layers.25.self_attn.out_proj",
+        "vision_model.encoder.layers.25.mlp.fc1",
+        "vision_model.encoder.layers.25.mlp.fc2",
+        "vision_model.embeddings.patch_embedding"
+      ]
+    },
+    "threads_per_block": [
+      512
+    ],
+    "version": "0.2.0"
+  },
+  "model_type": "qwen2"
+}

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": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

language_model_lm_head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f970cbcdf89259484199cede00c63ec9b77a813053d5d34e9bac49c3c140691
+size 752331275

language_model_model_embed_tokens.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c0d7ca5512aadc5f84560cda77c55078ff290a5b775f3b7de600ffb16963fe
+size 757042062

language_model_model_layers_0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f226700c4099d713eeb4cc9ddde0a71f0a02da2cb9f7dc6892f6c5c5ae92c243
+size 644111438

language_model_model_layers_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19239cd00c13705d2953f89e54551cc5c143f39e2e2f2c48ba4cb6473a9e920f
+size 638723406

language_model_model_layers_10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee07fcedc25098100107c0bca6e5a36203fc5d86ce193fb7e334d9e8358fd3fc
+size 629970167

language_model_model_layers_11.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6de99aa6f1010e7a31647c81808009a10de0af2fc48b7c61fe2ff0e2e8798f
+size 629893469

language_model_model_layers_12.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce72fcf8a2f30739681170906abd88b1e3f1037018fa5783edcba0b33000861
+size 630276225

language_model_model_layers_13.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b45caad6281bc0642a69d8e6c910de71aa758c3674f5c969a5c2729846bbd0
+size 630330097

language_model_model_layers_14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae6d739a0bfa9c42c69d0505d5b233e53db351326b85b774a0d9c3300f0eafb
+size 630619199

language_model_model_layers_15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9926aee78545fa79dcd355f5c88c6886df99abe97593da0b02e90d5169a5adc9
+size 630565950

language_model_model_layers_16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4750bf1aec1de352943b24dd6ed22aea2572da27d3613b560a5dbbd64eee33
+size 630474267

language_model_model_layers_17.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4656e2421ee96ba6feaece5e5e2b0d2c49d4cf20955f6a3c0d3acb36712fe5
+size 630544075

language_model_model_layers_18.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3db035f6f11a651949228fb2f4e78cc01cda87c086592dd327da025a9e9297
+size 630867707

language_model_model_layers_19.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f5173f5a35ee30666217a2429991a71a6eb12989731bb4208b1434ba2a82fb
+size 630750336

language_model_model_layers_2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc887462cab47f3456aac01d1ee7f01369510fb7c522954693bc77e0e5f095ef
+size 632274970

language_model_model_layers_20.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758bea036cc0ebe5eabea951608ce871f53365d29aad9e8559a7325cd2421138
+size 630878887

language_model_model_layers_21.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc4c2203a3a5325def758c5bd4d6190ba5cfa74e93425b041b4efa0e8244fd4
+size 631322419

language_model_model_layers_22.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7711c56709288b012550ab5defbe90e1ea4ef9cf119271b34dfdb169a9ef1ff
+size 631778764

language_model_model_layers_23.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cdc12ea279226a8872d80c32a5179df67218faf05683edf874961cb4019bf64
+size 631681079

language_model_model_layers_24.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83de5de1e071e65e63f76e8951ba1c465f7cd005ccfdcdcec2a5df38c9441fb
+size 631627171

language_model_model_layers_25.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8592d8cf7b848b54d7b5befdd55be2de907bda2aa7d008372585dd28158fbd64
+size 632434502

language_model_model_layers_26.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be9ef0d7bba09b8d856a5836599bb662e512f51ab8e5f6e8341ee4d5304204e
+size 633018168

language_model_model_layers_27.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552bbe022afa8e688203fa547779d943a24ea508feac3c37e9ca2833c59141ff
+size 635921761

language_model_model_layers_3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba9eeb3814894e3a929a2aad622327fc013063e388f561615f4a0893906292a
+size 631814768

language_model_model_layers_4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76af5c77a8baf08cba1a3fc57eff93800ab374029b97108d1e39ff75e68111cb
+size 632120936

language_model_model_layers_5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd3cb6072a21248a09a223ef83ddeee3fd9af7179e3de7ad974bdec0daa2d39
+size 631078745

language_model_model_layers_6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:122ab1ddd7a134c2165a4394482c0e0ba5fe397b45e698208978f983ff24a38b
+size 631993459

language_model_model_layers_7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcc43e31bd9d1fd696b855ea9a6e456bc92fae0bba48ea63006bec038e0c93d
+size 630749060

language_model_model_layers_8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570a186b7606516fa3a73268d45bee6500c399d154d73d053400a426bff7a5f1
+size 630408044

language_model_model_layers_9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04d9e0d946b38eb080aa83bdaa1f2f33b11997c64a571afec917b904fedba13
+size 632521026

llm_config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e0ba08e568360aa2c18e3de71026b4df4bf7618246d845a365de1439d280a1
+size 126925400

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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
+    }
+  },
+  "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    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\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{%- endif %}\n",
+  "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
+}

vae/ae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+size 335304388

vit_config.json

@@ -0,0 +1,9 @@
+{
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+}

vit_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d30db1bd6bed0c607acbbcb6c7b761c7515e1d7582c5f2a5aa958de24299cc9c
+size 550272394