Update tiny models for Glm4vForConditionalGeneration

.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 +1,33 @@
+[gMASK]<sop>
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- elif msg.role == 'user' %}
+<|user|>{{ '\n' }}
+
+        {%- if msg.content is string %}
+{{ msg.content }}
+        {%- else %}
+            {%- for item in msg.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 %}
+    {%- elif msg.role == 'assistant' %}
+        {%- if msg.metadata %}
+<|assistant|>{{ msg.metadata }}
+{{ msg.content }}
+        {%- else %}
+<|assistant|>
+{{ msg.content }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>
+{% endif %}

config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Glm4vForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_end_token_id": 6,
+  "image_start_token_id": 5,
+  "image_token_id": 7,
+  "model_type": "glm4v",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "eos_token_id": 151329,
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 22,
+    "max_position_embeddings": 512,
+    "model_type": "glm4v_text",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "output_channels": 64,
+    "pad_token_id": 151329,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "mrope_section": [
+        2,
+        1,
+        1
+      ],
+      "rope_theta": 10000,
+      "rope_type": "default",
+      "type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151352
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "video_end_token_id": 4,
+  "video_start_token_id": 3,
+  "video_token_id": 8,
+  "vision_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "depth": 2,
+    "hidden_act": "silu",
+    "hidden_size": 48,
+    "image_size": 336,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 22,
+    "model_type": "glm4v_vision",
+    "num_heads": 12,
+    "out_hidden_size": 16,
+    "patch_size": 14,
+    "rms_norm_eps": 1e-05,
+    "spatial_merge_size": 1,
+    "temporal_patch_size": 2
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 151329,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 151329,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b0956dfdddd3aa19290d5394fd0b30ca795a87183691d9f38a957ba93194fc
+size 19833264

preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "crop_size": {
+    "longest_edge": 336,
+    "shortest_edge": 336
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Glm4vImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "merge_size": 2,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 336,
+    "shortest_edge": 336
+  },
+  "temporal_patch_size": 2
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc742fc44db1f0870d7320b495e6240cc40e202565fc96786220fa0d9ddb41c
+size 19968183

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "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|>",
+    "<|image|>",
+    "<|video|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 65536,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}

video_preprocessor_config.json

@@ -0,0 +1,38 @@
+{
+  "crop_size": {
+    "longest_edge": 336,
+    "shortest_edge": 336
+  },
+  "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": 336,
+    "shortest_edge": 336
+  },
+  "temporal_patch_size": 2,
+  "video_processor_type": "Glm4vVideoProcessor"
+}