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 +1,23 @@
+---
+language:
+- zh
+- en
+library_name: transformers
+license: mit
+pipeline_tag: image-text-to-text
+tags:
+- mlx
+---
+
+# animaslabs/GLM-4.6V-Flash-4bit
+This model was converted to MLX format from [`zai-org/GLM-4.6V-Flash`]() using mlx-vlm version **0.3.12**.
+Refer to the [original model card](https://huggingface.co/zai-org/GLM-4.6V-Flash) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model animaslabs/GLM-4.6V-Flash-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

chat_template.jinja

@@ -0,0 +1,140 @@
+[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 -%}
+{%- 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 +1,82 @@
+{
+    "architectures": [
+        "Glm4vForConditionalGeneration"
+    ],
+    "eos_token_id": [
+        151329,
+        151336,
+        151338,
+        151348
+    ],
+    "image_end_token_id": 151340,
+    "image_start_token_id": 151339,
+    "image_token_id": 151363,
+    "model_type": "glm4v",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "text_config": {
+        "attention_bias": true,
+        "attention_dropout": 0.0,
+        "dtype": "bfloat16",
+        "eos_token_id": [
+            151329,
+            151336,
+            151338
+        ],
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "initializer_range": 0.02,
+        "intermediate_size": 13696,
+        "max_position_embeddings": 131072,
+        "model_type": "glm4v_text",
+        "num_attention_heads": 32,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 2,
+        "pad_token_id": 151329,
+        "rms_norm_eps": 1e-05,
+        "rope_parameters": {
+            "mrope_section": [
+                8,
+                12,
+                12
+            ],
+            "partial_rotary_factor": 0.5,
+            "rope_theta": 500000,
+            "rope_type": "default"
+        },
+        "use_cache": true,
+        "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": 13696,
+        "model_type": "glm4v_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 +1,15 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338,
+    151348
+  ],
+  "pad_token_id": 151329,
+  "top_p": 0.6,
+  "temperature": 0.8,
+  "top_k": 2,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1070400b73b939d66b23430bc967605e78c6a2e8998b0244be76825970aca575
+size 5367706660

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f108750978956604628172d94c058651bee690e5ca9904a021bc0671aa8accd5
+size 1706311094

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 +1,66 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Glm46VImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 9633792,
+      "shortest_edge": 12544
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Glm46VProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "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
+    ],
+    "max_duration": 300,
+    "max_image_size": {
+      "longest_edge": 47040000
+    },
+    "merge_size": 2,
+    "num_frames": 16,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 100352000,
+      "shortest_edge": 12544
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Glm46VVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
+size 19970700

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "is_local": true,
+  "model_max_length": 128000,
+  "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": 100352000},
+    "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"
+}