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

chat_template.jinja

@@ -0,0 +1,141 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
+                <|begin_of_image|><|image|><|end_of_image|>
+            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
+                <|begin_of_video|><|video|><|end_of_video|>
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{% if m.content is string %}
+{{ m.content }}
+{%- else %}
+{%- for item in m.content %}
+{% if item.type == 'video' or 'video' in item %}
+<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
+<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
+{{ item.text }}
+{%- endif %}
+{%- endfor %}
+{%- endif %}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{% elif m.content is iterable and m.content is not mapping %}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+{{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{%- for tr in m.content -%}
+  {%- if tr is mapping and tr.type is defined -%}
+    {%- set t = tr.type | lower -%}
+    {%- if t == 'text' and tr.text is defined -%}
+{{ tr.text }}
+    {%- elif t in ['image', 'image_url'] -%}
+<|begin_of_image|><|image|><|end_of_image|>
+    {%- elif t in ['video', 'video_url'] -%}
+<|begin_of_video|><|video|><|end_of_video|>
+    {%- else -%}
+{{ tr | tojson(ensure_ascii=False) }}
+    {%- endif -%}
+  {%- else -%}
+{{ tr.output if tr.output is defined else tr }}
+  {%- endif -%}
+{%- endfor -%}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{# ====== 逻辑结束 ====== #}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|assistant|>
+{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
+{%- endif -%}

config.json

@@ -0,0 +1,90 @@
+{
+    "architectures": [
+        "Glm4vMoeForConditionalGeneration"
+    ],
+    "image_end_token_id": 151340,
+    "image_start_token_id": 151339,
+    "image_token_id": 151363,
+    "model_type": "glm4v_moe",
+    "quantization": {
+        "group_size": 128,
+        "bits": 3,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 128,
+        "bits": 3,
+        "mode": "affine"
+    },
+    "text_config": {
+        "attention_bias": true,
+        "attention_dropout": 0.0,
+        "dtype": "bfloat16",
+        "eos_token_id": [
+            151329,
+            151336,
+            151338
+        ],
+        "first_k_dense_replace": 1,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "initializer_range": 0.02,
+        "intermediate_size": 10944,
+        "max_position_embeddings": 131072,
+        "model_type": "glm4v_moe_text",
+        "moe_intermediate_size": 1408,
+        "n_group": 1,
+        "n_routed_experts": 128,
+        "n_shared_experts": 1,
+        "norm_topk_prob": true,
+        "num_attention_heads": 96,
+        "num_experts_per_tok": 8,
+        "num_hidden_layers": 46,
+        "num_key_value_heads": 8,
+        "num_nextn_predict_layers": 0,
+        "pad_token_id": 151329,
+        "partial_rotary_factor": 0.5,
+        "qk_layernorm": false,
+        "rms_norm_eps": 1e-05,
+        "rope_parameters": {
+            "mrope_section": [
+                8,
+                12,
+                12
+            ],
+            "partial_rotary_factor": 0.5,
+            "rope_theta": 500000,
+            "rope_type": "default"
+        },
+        "routed_scaling_factor": 1.0,
+        "topk_group": 1,
+        "use_cache": true,
+        "use_qk_norm": false,
+        "vocab_size": 151552
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "5.0.0rc0",
+    "video_end_token_id": 151342,
+    "video_start_token_id": 151341,
+    "video_token_id": 151364,
+    "vision_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "depth": 24,
+        "hidden_act": "silu",
+        "hidden_dropout_prob": 0.0,
+        "hidden_size": 1536,
+        "image_size": 336,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 10944,
+        "model_type": "glm4v_moe_vision",
+        "num_heads": 12,
+        "out_hidden_size": 4096,
+        "patch_size": 14,
+        "rms_norm_eps": 1e-05,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "top_p": 0.6,
+  "temperature": 0.8,
+  "top_k": 2,
+  "transformers_version": "5.0.0rc0"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac4bbf64ee7408108781c78f8e101559cb6b217d2d9dee230f5f3858c6630ce
+size 5340544345

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370bb3d2f91218c24ebad159d09033eacf8ede38426aea320a4d111ac51cd7af
+size 5368424302

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157a3fc5180d491412c15bdfdce5bd23e7d2e9fcdaeb564c6f8ceb1306b26a5d
+size 5104768329

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bcadea3ad1ae8adaa6f54c18684e9af33aad2864bb012476c39730b0533afd
+size 5368424520

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d40f8c89c91b839f7f2bdbb22160a46a65587595f317b152076c5e2cb7a6ed2
+size 5104768327

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef2b5415b828fbffab9f2a901797c4bb41c65728489071d83a40364bd17d3db
+size 5368424528

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d441fad8712f15d3fe38cbc498b142532d2b0f0b9b8238d0329f4bad1b9547
+size 5104768381

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db699082d3683ddcaa34cfbacc2249251481e05542d4e01d8dd836d40c014df8
+size 5368424490

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57e6ab5d9dde036d271505711c972817bb02cceebe6f7c2401e68e45e3f05fb
+size 3108516475

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+    "size": {"shortest_edge": 12544, "longest_edge": 9633792},
+    "do_rescale": true,
+    "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": "Glm46VImageProcessor",
+    "processor_class": "Glm46VProcessor"
+}

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Glm46VImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "processor_class": "Glm46VProcessor",
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 9633792,
+      "shortest_edge": 12544
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Glm46VProcessor",
+  "video_processor": {
+    "crop_size": null,
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "device": null,
+    "do_center_crop": null,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_pad": null,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "input_data_format": null,
+    "max_duration": 300,
+    "max_image_size": {
+      "longest_edge": 47040000
+    },
+    "merge_size": 2,
+    "num_frames": 16,
+    "pad_size": null,
+    "patch_size": 14,
+    "processor_class": "Glm46VProcessor",
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "return_tensors": null,
+    "size": {
+      "longest_edge": 47040000,
+      "shortest_edge": 12544
+    },
+    "temporal_patch_size": 2,
+    "video_metadata": null,
+    "video_processor_type": "Glm46VVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ccf2252fe9cd23ada23a829ec409aab397dbd2ac4f372d3a1a23d1f7c72d6b
+size 19970686

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|image|>",
+    "<|video|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|image|>",
+    "<|video|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "is_local": true,
+  "model_max_length": 128000,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "Glm46VProcessor",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}

video_preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+    "size": {"shortest_edge": 12544, "longest_edge": 47040000},
+    "do_rescale": true,
+    "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],
+    "video_processor_type": "Glm46VVideoProcessor",
+    "processor_class": "Glm46VProcessor"
+}