Update tiny models for GlmImageTextModel

.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 +1,13 @@
+{%- for m in messages -%}
+    {%- if m.content is string -%}
+        {{ m.content }}
+    {%- else -%}
+        {%- for item in m.content -%}
+            {%- if item.type == 'image' or item.get('image') is not none -%}
+            <|dit_token_16384|><|image|><|dit_token_16385|>
+            {%- elif item.type == 'text' -%}
+                {{ item.text }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+{%- endfor -%}

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "GlmImageTextModel"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 16384,
+  "dtype": "float32",
+  "eos_token_id": 16385,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 22,
+  "max_position_embeddings": 512,
+  "model_type": "glm_image_text",
+  "n_group": 1,
+  "n_routed_experts": 8,
+  "n_shared_experts": 1,
+  "num_attention_heads": 2,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "output_channels": 64,
+  "pad_token_id": 16385,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "mrope_section": [
+      2,
+      1,
+      1
+    ],
+    "rope_theta": 10000,
+    "rope_type": "default",
+    "type": "default"
+  },
+  "tie_word_embeddings": true,
+  "topk_group": 1,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vision_vocab_size": 99,
+  "vocab_size": 167864
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fa56c8881d83723cd57307138db3e4b0e60ca8fa531c7e6872cf5a7114a237
+size 10761544

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "GlmImageImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "merge_size": 1,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 4194304,
+    "shortest_edge": 262144
+  },
+  "temporal_patch_size": 1
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d771c9659fd2c65c0ef8a8daf9d9f9f07b53f89ce164cc832a28137db604d01d
+size 23765636

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|dit_token_16384|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|dit_token_16385|>",
+  "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|>"
+  ],
+  "grid_bos_token": "<sop>",
+  "grid_eos_token": "<eop>",
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "model_specific_special_tokens": {
+    "grid_bos_token": "<sop>",
+    "grid_eos_token": "<eop>",
+    "image_token": "<|image|>"
+  },
+  "pad_token": "<|dit_token_16385|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}