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 +1,44 @@
+{{ bos_token }}{%- if messages[0]['role'] == 'system' -%}
+    {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<|turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'audio' -%}
+                {{ '<|audio|>' }}
+            {%- elif item['type'] == 'image' -%}
+                {{ '<|image|>' }}
+            {%- elif item['type'] == 'video' -%}
+                {{ '<|video|>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<turn|>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<|turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,192 @@
+{
+    "architectures": [
+        "Gemma4ForConditionalGeneration"
+    ],
+    "audio_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "attention_chunk_size": 12,
+        "attention_context_left": 13,
+        "attention_context_right": 0,
+        "attention_invalid_logits_value": -1000000000.0,
+        "attention_logit_cap": 50.0,
+        "chunk_size_feed_forward": 0,
+        "conv_kernel_size": 5,
+        "torch_dtype": "float16",
+        "gradient_clipping": 10000000000.0,
+        "hidden_act": "silu",
+        "hidden_size": 1024,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "model_type": "gemma4_audio",
+        "num_attention_heads": 8,
+        "num_hidden_layers": 12,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_proj_dims": 1536,
+        "problem_type": null,
+        "residual_weight": 0.5,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06,
+        "subsampling_conv_channels": [
+            128,
+            32
+        ],
+        "use_clipped_linears": true
+    },
+    "audio_token_id": 258881,
+    "boa_token_id": 256000,
+    "boi_token_id": 255999,
+    "torch_dtype": "float16",
+    "eoa_token_id": 258883,
+    "eoa_token_index": 258883,
+    "eoi_token_id": 258882,
+    "eos_token_id": 106,
+    "image_token_id": 258880,
+    "initializer_range": 0.02,
+    "model_name": "unsloth/gemma-4-E2B-it",
+    "model_type": "gemma4",
+    "pad_token_id": 0,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attention_k_eq_v": false,
+        "bos_token_id": 2,
+        "torch_dtype": "float16",
+        "enable_moe_block": false,
+        "eos_token_id": 1,
+        "expert_intermediate_size": null,
+        "final_logit_softcapping": 30.0,
+        "global_head_dim": 512,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 1536,
+        "hidden_size_per_layer_input": 256,
+        "initializer_range": 0.02,
+        "intermediate_size": 6144,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention"
+        ],
+        "max_position_embeddings": 131072,
+        "model_type": "gemma4_text",
+        "moe_intermediate_size": null,
+        "num_attention_heads": 8,
+        "num_experts": null,
+        "num_global_key_value_heads": null,
+        "num_hidden_layers": 35,
+        "num_key_value_heads": 1,
+        "num_kv_shared_layers": 20,
+        "pad_token_id": 0,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "full_attention": {
+                "partial_rotary_factor": 0.25,
+                "rope_theta": 1000000.0,
+                "rope_type": "proportional"
+            },
+            "sliding_attention": {
+                "rope_theta": 10000.0,
+                "rope_type": "default"
+            }
+        },
+        "sliding_window": 512,
+        "tie_word_embeddings": true,
+        "top_k_experts": null,
+        "use_bidirectional_attention": null,
+        "use_cache": true,
+        "use_double_wide_mlp": true,
+        "vocab_size": 262144,
+        "vocab_size_per_layer_input": 262144
+    },
+    "tie_word_embeddings": true,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.4.4",
+    "use_cache": false,
+    "video_token_id": 258884,
+    "vision_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "chunk_size_feed_forward": 0,
+        "default_output_length": 280,
+        "torch_dtype": "float16",
+        "global_head_dim": 64,
+        "head_dim": 64,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 768,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "intermediate_size": 3072,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "max_position_embeddings": 131072,
+        "model_type": "gemma4_vision",
+        "num_attention_heads": 12,
+        "num_hidden_layers": 16,
+        "num_key_value_heads": 12,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "patch_size": 16,
+        "pooling_kernel_size": 3,
+        "position_embedding_size": 10240,
+        "problem_type": null,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "rope_theta": 100.0,
+            "rope_type": "default"
+        },
+        "standardize": false,
+        "use_clipped_linears": true
+    },
+    "vision_soft_tokens_per_image": 280
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26e99e1fa290296828da6d00423b5557125badf7dc8d05f84dfd4f71e35b688
+size 1422130752

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea02bad44856b48a53786446e9d32217ea9c377b26d16032919b8785c2b87be
+size 4697620648

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85cebd4f098a5d61a725613814958869c645b022e6a7c083e69404732cd541b4
+size 1585731424

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c9af61512ebc3638f059520521759ec7846029c1408fb18372b3dd3410213a
+size 1573107586

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effad452196792688548cadc772fe211ed03e159254ceffb31e54124c30491ed
+size 968028372

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "left",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

tokenizer_config.json

@@ -0,0 +1,96 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<turn|>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "chat_template": "{{ bos_token }}{%- if messages[0]['role'] == 'system' -%}\n    {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<|turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'audio' -%}\n                {{ '<|audio|>' }}\n            {%- elif item['type'] == 'image' -%}\n                {{ '<|image|>' }}\n            {%- elif item['type'] == 'video' -%}\n                {{ '<|video|>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<turn|>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<|turn>model\n'}}\n{%- endif -%}\n"
+}