Add files using upload-large-folder tool

chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% macro render_content(content) %} {% if content is string %}{{- content }}{% elif content is mapping %}{{- content['value'] if 'value' in content else content['text'] }}{% elif content is iterable %}{% for item in content %}{% if item.type == 'text' %}{{- item['value'] if 'value' in item else item['text'] }}{% elif item.type == 'image' %}<im_patch>{% endif %}{% endfor %}{% endif %} {% endmacro %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message.role == 'system' %}{{ render_content(message['content']) }}{% endif %}{% endfor %}{% if tools is defined and tools %}{% set ns = namespace(data='') %}{% for tool in tools %}{% set ns.data = ns.data + (tool | tojson(ensure_ascii=False)) + '\n' %}{% endfor %}{% set tool_schemas_var = ns.data %}# Tools \nYou may call one or more tools to assist with the user query. You are provided with tool schemas within <tools></tools> XML tags: <tools>{{ tool_schemas_var }}</tools> When making tool calls, use XML format to invoke tools and pass parameters: <｜tool_calls_begin｜>\n<｜tool_call_begin｜>\nfunction<｜tool_sep｜><steptml:invoke name=\"tool_name0\"><steptml:parameter name=\"parameter_name0\">[parameter value]</steptml:parameter>...</steptml:invoke><｜tool_call_end｜>\n<｜tool_call_begin｜>\nfunction<｜tool_sep｜><steptml:invoke name=\"tool_name1\"><steptml:parameter name=\"parameter_name1\">[parameter value]</steptml:parameter>...</steptml:invoke><｜tool_call_end｜>\n<｜tool_calls_end｜>\nNote: * You can invoke one or more tools in parallel. * Each tool call must be complete and self-contained within a single <steptml:toolcall></steptml:toolcall> block. {% endif %}{% for message in messages %}{% if message.role == 'tool_description' %}{{ render_content(message['content']) }}{% elif message.role == 'user' %}{{- '<|BOT|>' + message.role + '\\n' + render_content(message['content']) }}{{- '<|EOT|>' }}{% elif message.role == 'tool_response' %}<｜tool_outputs_begin｜>\n{% for tool_output in message['content'] %}<｜tool_output_begin｜>\n{{ render_content(tool_output) }}<｜tool_output_end｜>{% endfor %}\n<｜tool_outputs_end｜>\n{% else %}{{- '<|BOT|>' + message.role + '\n' }}{% if message['content'] is defined %}{{- render_content(message['content']) }}{% endif %}{% if message.tool_calls is defined %}<｜tool_calls_begin｜>\n{% for tool in message.tool_calls %}<｜tool_call_begin>｜>\n{{ tool['type'] }}<｜tool_sep｜>{{- '<steptml:invoke name=\"' + tool['function']['name'] + '\">' }}{% for name, param in tool['function']['arguments'].items() %} {{- '<steptml:parameter name=\"' + name + '\">' + param | string + '</steptml:parameter>' }}{% endfor %}</steptml:invoke><｜tool_call_end｜>\n{% endfor %}<｜tool_calls_end｜>\n{% endif %}<|EOT|>{% endif %}{% endfor %}{% if add_generation_prompt %}{{- '<|BOT|>assistant\n<think>\n' }}{% endif %}"
+}

config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "Step3VLForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_step3.Step3VLConfig",
+    "AutoModelForCausalLM": "modeling_step3.Step3vForConditionalGeneration"
+  },
+  "model_type": "step3_vl",
+  "im_end_token": "<im_end>",
+  "im_patch_token": "<im_patch>",
+  "im_start_token": "<im_start>",
+  "image_token_len": 169,
+  "patch_token_len": 81,
+  "understand_projector_stride": 2,
+  "projector_bias": false,
+  "image_token_id": 128001,
+  "bos_token_id": 0,
+  "eos_token_id": 128805,
+  "text_config": {
+    "architectures": [
+      "Step3TextForCausalLM"
+    ],
+    "model_type": "step3_text",
+    "hidden_size": 7168,
+    "intermediate_size": 18432,
+    "num_hidden_layers": 61,
+    "max_seq_len": 65536,
+    "max_position_embedding": 65536,
+    "vocab_size": 128815,
+    "torch_dtype": "bfloat16",
+    "moe_layers_enum": "4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59",
+    "num_attention_heads": 64,
+    "num_attention_groups": 1,
+    "head_dim": 256,
+    "share_q_dim": 2048,
+    "moe_num_experts": 48,
+    "moe_top_k": 3,
+    "moe_intermediate_size": 5120,
+    "share_expert_dim": 5120,
+    "norm_expert_weight": false,
+    "rope_theta": 500000
+  },
+  "vision_config": {
+    "hidden_size": 1792,
+    "output_hidden_size": 4096,
+    "image_size": 728,
+    "intermediate_size": 15360,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 63,
+    "patch_size": 14
+  }
+}

configuration_step3.py

@@ -0,0 +1,120 @@
+from typing import Any, Optional, Union
+
+from transformers.configuration_utils import PretrainedConfig
+
+
+class Step3VisionEncoderConfig(PretrainedConfig):
+    model_type = "step3_vision_encoder"
+
+    def __init__(
+        self,
+        hidden_size=1792,
+        intermediate_size=3072,
+        output_hidden_size=4096,
+        num_hidden_layers=63,
+        num_attention_heads=16,
+        num_channels=3,
+        image_size=728,
+        patch_size=14,
+        hidden_act="quick_gelu",
+        layer_norm_eps=1e-5,
+        **kwargs,
+    ):
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.output_hidden_size = output_hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_channels = num_channels
+        self.patch_size = patch_size
+        self.image_size = image_size
+        self.layer_norm_eps = layer_norm_eps
+        self.hidden_act = hidden_act
+        super().__init__(**kwargs)
+
+
+class Step3TextConfig(PretrainedConfig):
+    model_type = "step3_text"
+    architectures = ["Step3TextForCausalLM"]
+
+    def __init__(
+        self,
+        hidden_size: int = 7168,
+        intermediate_size: int = 18432,
+        num_attention_heads: int = 64,
+        num_attention_groups: int = 1,
+        num_hidden_layers: int = 61,
+        max_seq_len: int = 65536,
+        vocab_size: int = 128815,
+        rms_norm_eps: float = 1e-5,
+        moe_intermediate_size: int = 5120,
+        moe_num_experts: int = 48,
+        moe_top_k: int = 3,
+        rope_theta: float = 500000,
+        rope_scaling: Optional[dict[str, Any]] = None,
+        max_position_embedding: int = 65536,
+        share_expert_dim: int = 5120,
+        share_q_dim: int = 2048,
+        head_dim: int = 256,
+        norm_expert_weight: bool = False,
+        moe_layers_enum: tuple[int] = (4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
+                                       15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
+                                       25, 26, 27, 28, 29, 30, 31, 32, 33, 34,
+                                       35, 36, 37, 38, 39, 40, 41, 42, 43, 44,
+                                       45, 46, 47, 48, 49, 50, 51, 52, 53, 54,
+                                       55, 56, 57, 58, 59),
+        **kwargs,
+    ) -> None:
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_attention_heads = num_attention_heads
+        self.num_attention_groups = num_attention_groups
+        self.num_hidden_layers = num_hidden_layers
+        self.max_seq_len = max_seq_len
+        self.vocab_size = vocab_size
+        self.rms_norm_eps = rms_norm_eps
+        self.moe_intermediate_size = moe_intermediate_size
+        self.moe_num_experts = moe_num_experts
+        self.moe_top_k = moe_top_k
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.max_position_embedding = max_position_embedding
+        self.share_expert_dim = share_expert_dim
+        self.share_q_dim = share_q_dim
+        self.head_dim = head_dim
+        self.norm_expert_weight = norm_expert_weight
+        self.moe_layers_enum = moe_layers_enum
+
+        super().__init__(**kwargs)
+
+
+class Step3VLConfig(PretrainedConfig):
+    model_type = "step3_vl"
+
+    def __init__(
+        self,
+        vision_config: Optional[Union[dict, Step3VisionEncoderConfig]] = None,
+        text_config: Optional[Union[dict, Step3TextConfig]] = None,
+        understand_projector_stride: int = 1,
+        projector_bias: bool = True,
+        image_token_id: int = 128001,
+        **kwargs,
+    ) -> None:
+        if vision_config is None:
+            vision_config = Step3VisionEncoderConfig()
+        elif isinstance(vision_config, dict):
+            vision_config = Step3VisionEncoderConfig(**vision_config)
+        self.vision_config = vision_config
+
+        if text_config is None:
+            text_config = Step3TextConfig()
+        elif isinstance(text_config, dict):
+            text_config = Step3TextConfig(**text_config)
+        self.text_config = text_config
+
+        self.understand_projector_stride = understand_projector_stride
+        self.projector_bias = projector_bias
+        self.hidden_size = text_config.hidden_size
+        self.image_token_id = image_token_id
+
+        super().__init__(**kwargs)

generation_config.json

@@ -0,0 +1,8 @@
+{
+    "bos_token_id": 0,
+    "eos_token_id": 128805,
+    "temperature": 0.7,
+    "top_p": 0.95,
+    "do_sample": true,
+    "transformers_version": "4.54.0"
+}

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d116ae88ed10f56742606e2da7818e1533988297a3006cd6791182059a9b3226
+size 9955092120

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e8bc428a78e1781d7eeaef0cf32a547d7a4189178f4e84675e3f7aa9c9790c
+size 9957541368

model-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e2a0d26a1131a46a6df4deaf7337d8dbdbd9002809728b55c978b28960fadb
+size 9966049896

model-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94ccd8c0c564e9df04a693208435f9b40736ef0e00d3d4c2891e2c7fe50c65e
+size 9975131928

model-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2012990f05f356635c3856aee2dbf1fa383ce641a9e0c1a547bb37cc4674d2
+size 9921772592

model-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a5a3f511975156d039cf531e42cfbd5ecbdffb8ff0d29b29d8c7d4ca6cf05b
+size 7310672224

model-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9242859c3de930b9d2535807edb1a253c6b4759f1160bf35b717d33ee66869
+size 7046430952

model-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9197980060dd760b08efde286c40e165ed0bdd8f4c9cfea7152b1c38260ec194
+size 7046430952

model-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e6923a6705304f11c9dd3c11255f1d688e01a4f51514189404463637a6b021
+size 7046430960

model-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c6aeba446a0f4a0c0fd9c47f712d60f9805ab251cb2790c0288d4275141145
+size 7046430952

model-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebf56573462ed491301b008bc57d3b25f2665d9a7aaf6f6a2265bb108992244
+size 7046430952

model-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e839654a313b7d78cae825323f9a06f6d6c394fabfea353fa9e76c799339269
+size 7046430960

model-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c791af2fe41f79cda4e278dc891bdc2a0753b14b9afd475f27ff810d0f3965a4
+size 7046430952

model-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3380f3e2160f3733feddfdd94b94f75e9e85131a5797ba0e1bf4f2065c54a25f
+size 7046430952

model-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f522596a3bea36902c309ffaf864cd640cc275978f10c006a78a816bbbfa49
+size 7046430960

model-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81cbf3a31597fc070cf9f13419a7df1f18949e0fc8086780fad4de390f0c5d32
+size 7046430960

model-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd37184a4d54b3e303eb0ea3b8d3f3e396adaffb993d49097edd5f2818912a6
+size 7046430960

model-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543462296f44f57710405ee5df48dccdc7a28ec75170b6111b841d17a5fcdfd9
+size 7046430960

model-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bdba8a5242c255127bc887c2159ae76e947e8fa9eb9474736be166c4e98b6c
+size 7046430960

model-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07cc863fc86cc9eb5d1bab06f593de41c5cd36a9231f4edc133c07ce1aefd74
+size 7046430960

model-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cac9d71d0ac36a460f3bf39da1f95d4335c02d9b6e9332e3042adbbfeba1a1
+size 7046430960

model-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5db4f8395f0a5c71b26a227b04ad5a663b31e178a6da1ede1a243fc8c418e25
+size 7046430960

model-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229ba45a9cd8b8792a5b83b7148ca13f8c4cb3f2443546a3aa4e4d3f53bb6291
+size 7046430960

model-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095e4450b4c83f545ad450fc39b9c7d995f7f842b8c7802dc7485e4817ac46a0
+size 7046430960

model-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8050270d6c6a289cd3889a7b6aaed62fe50380ada7b887cbd3b4a7bed0d55e
+size 7046430960

model-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49a63250dc25e5d3f25dd1d002722f203b8a7e5d4c7742e3bf0690a1c1632e4
+size 7046430960

model-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dcbc3771b950d73ac97ce54d20b22090551fea9a4cd37bc4d953261c5cd5dd
+size 7046430960

model-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76ce1a53cfb59a0afb3bfd6ce5deabf6bbc3a84aaa0379e29d93d09e1a0a326
+size 7046430960

model-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0add3917e46cc0be92ac9230a413ff010a4437695ccc4df7ac056f085984788d
+size 7046430960

model-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1a4e9becd74c663a24dcb043bfda7797c4127368dd58eefe85ba09610dd73e
+size 7046430960

model-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff8d05fd4803bbbbd685ada90bda51c6b99bb2b12a8dbc36910eb0ef9dc7803
+size 7046430960

model-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb58c7424bb3fb0c0d5c84f4cb7b220deb73cd677a5bb509ab782567a1f8a687
+size 7046430960

model-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac34581b2fb405be199b99b71356b60caf1f2c64ad5fe92dd14a3aa6b156ba3
+size 7046430960

model-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9fc7d48f75050201c785b5973c8517fd4c82a95787772ec9e48fad400e4233
+size 7046430960

model-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32bffd85be89f836ca36ed7201aaa676b93a4db9ca9be4fd36094dc93d16d3b
+size 7046430960

model-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb6e50876d8477768af98c35fb7268dff1897e037d7506b3d295547d75bcfcc
+size 7046430960

model-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756125d247a87695e01627d274078d8e20b4f7e45a2455021c4c287e613062ff
+size 7046430960

model-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbbd03054fa79da17d279ae1839fcfd79de63ed56352c896b1f6f31cc93e8c8
+size 7046430960

model-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71671759930fe237c9f896a47369b6d04ac895ede6d5cb7dfbe558dd810af92a
+size 7046430960

model-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6fb17111f7af6863b77178fb96366475ed3b6ead0f806f924dd18a5504048a
+size 7046430960

model-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af14b4f09b9665cd3ec3b86b410ac781b837c33b7efbe320869ad265f02f69db
+size 7046430960

model-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8178740784101d98781f429a57e66cc1f1e34d5d6db0c2bfcfc9e0239e65ca
+size 7046430960

model-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d11e4cdba8b59590e6e9c5c747fcd00434d8a2446d28055d8ed7dc17855e630
+size 7046430960

model-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9e9fbee686e078de3b1cad1c10575cbcd36b544cdca826565492b7331a98c6
+size 7046430960

model-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87083ba08825811bea75c96f7d48de98104568858c7c2540448a0ec71064c587
+size 7046430960

model-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4140d24b7638e5ad043ae178d041eea74b498d1708e5867eb358874bfff09ffc
+size 7046430960