Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+base_model:
+- allura-org/Teleut-7b
+- EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [allura-org/Teleut-7b](https://huggingface.co/allura-org/Teleut-7b)
+* [EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+- sources:
+  - layer_range: [0, 4]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [3, 4] 
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [4, 8]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [7, 8]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [8, 12]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [11, 12]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [12, 16]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [15, 16]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [16, 20]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [19, 20]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [20, 28]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+merge_method: passthrough
+dtype: bfloat16
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "allura-org/Teleut-7b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 33,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,36 @@
+slices:
+- sources:
+  - layer_range: [0, 4]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [3, 4] 
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [4, 8]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [7, 8]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [8, 12]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [11, 12]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [12, 16]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [15, 16]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [16, 20]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+- sources:
+  - layer_range: [19, 20]
+    model: allura-org/Teleut-7b
+- sources:
+  - layer_range: [20, 28]
+    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8aa26a04efea407b900b2ccd8c14eaaa71adb68cbf77a28fe6678e39014a68d
+size 1089994880

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bd781198bf9c4906d8a52fc447928826a1c83212e37089ffb7a02f0847c00b
+size 1089994896

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c9ed73b8fb932c6e9e22ad8b06d6cfef0bcd8d606cc40640bfefef6c3a58ac
+size 932241160

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3530a1e3a9f14aa7c8bfbb6aef1f7f967b807af515b21768a807357e9752d5
+size 873496368

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfcb4834f096d7098ca88639888aaa12e9bbfac2b64bd3605e1c5f9b5b82f30e
+size 990971456

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143b03d945ecb877f88e94a81eff5281d94a87f6d2fdc77ee4b99a4c72366331
+size 932241192

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc27e08c951b910cdd723ed5bcc068cb943df0e669f57669eadd5e462d42e68
+size 932226640

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd985c4f1e9f8c4d26d464cfc45d17a25b1041fdf612c476319dac375a3f8cc9
+size 932233912

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72015cc3f65ddd1e817e2fe6255a6f9756e94c346fcb83cf3123a69b6f71706
+size 873496368

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e775331874c1129cf93f89ea755ba01e2a92e62c96e11a3d15bc85f6348f591
+size 990971440

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69854e29bdd1a7dafb9d2d6114a948bbf9c1b86976c93206bc3eb98e2cec0bd7
+size 932233912

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d627175ae4565dea08359fac434650ecadc8fa0438b5f1c0c808cfa6e2affb60
+size 932233912

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c64a74b42b1bf23c82aae8dae8a1cce843a23f3e3c4b5bd7f3f829193f452e3
+size 932233912

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdd6e09ffd8c3aa602618184be411bad69fa2f13e94d7f4f16132a8a6d1c893
+size 932241184

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94051fcf4ffd119568cefd659dd909c8498f2da431ce9acf780c6347c1ffc1c8
+size 932226616

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ba29cf9d6714c8596614c74a73a7ee931330a41177d2c6b6c8c923f0bd81dc
+size 932233888

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48949c2f05fe8a943ad872207fe3e31125510f774966ae06fa02666365a8febd
+size 873496352

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6093244e82519ac964d89ed41d696f05f16800dee4d8d2a37f15bad465e1a4e
+size 990971432

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9737e5ef157554f1c5256c1242e3963cac0e00775b60bdf2230861b405b7fbd9
+size 466116952

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 17561810944}, "weight_map": {"lm_head.weight": "model-00001-of-00019.safetensors", "model.embed_tokens.weight": "model-00002-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00019.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00010-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00019.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00010-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00012-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00012-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00012-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00013-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00013-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00013-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00013-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00013-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00013-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00014-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.32.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00014-of-00019.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00014-of-00019.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00014-of-00019.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00015-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00015-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00015-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00016-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00016-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00016-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

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 not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}