Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}"
+}

config.json

@@ -0,0 +1,185 @@
+{
+  "architectures": [
+    "Phi4MultimodalForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_config": {
+    "activation": "swish",
+    "audio_token_id": 200011,
+    "bias_max_distance": 500,
+    "bias_symmetric": false,
+    "chunk_size": -1,
+    "conv_activation": "swish",
+    "conv_glu_type": "swish",
+    "depthwise_multiplier": 1,
+    "depthwise_seperable_out_channel": 1024,
+    "downsample_rate": 1,
+    "dropout_rate": 0.0,
+    "ext_pw_out_channel": 1024,
+    "feature_layer": -2,
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "input_size": 80,
+    "intermediate_size": 1536,
+    "kernel_size": 3,
+    "left_chunk": 18,
+    "model_type": "phi4_multimodal_audio",
+    "nemo_activation": "relu",
+    "nemo_conv_channels": 1024,
+    "nemo_final_size": 10,
+    "num_attention_heads": 16,
+    "num_blocks": 24,
+    "time_reduction": 8
+  },
+  "bos_token_id": 199999,
+  "embd_pdrop": 0.0,
+  "eos_token_id": [
+    199999,
+    200020
+  ],
+  "full_attn_mod": 1,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi4_multimodal",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 199999,
+  "partial_rotary_factor": 0.75,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "short_factor": [
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0.dev0",
+  "use_cache": true,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "crop_size": 448,
+    "feature_layer": -2,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 448,
+    "image_token_id": 200010,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "phi4_multimodal_vision",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  },
+  "vocab_size": 200064
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 199999,
+  "eos_token_id": [
+    199999,
+    200020
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.51.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b93f5d0c9422c0b76b68119660187989bd8bb47848994376be3ac53eb61a95
+size 4903637712

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6f60df08041b5c48afe7d7624d4de6e9d7d86162dec7a7e908a71d595e2967
+size 4584575136

preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "audio_compression_rate": 8,
+  "audio_downsample_rate": 1,
+  "audio_feat_stride": 1,
+  "dynamic_hd": 36,
+  "feature_extractor_type": "Phi4MultimodalFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "image_processor_type": "Phi4MMImageProcessor",
+  "n_fft": 512,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "preemphasis": 0.97,
+  "processor_class": "Phi4MultimodalProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_length": 400
+}

processor_config.json

@@ -0,0 +1,5 @@
+{
+  "fake_audio_token_pattern": "<\\|audio_\\d+\\|>",
+  "fake_image_token_pattern": "<\\|image_\\d+\\|>",
+  "processor_class": "Phi4MultimodalProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1b9f641d4f8b7247b8d5007dd3b6a9f6a87cb5123134fe0d326f14d10c0585
+size 15524479

tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|endoftext10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|endoftext11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "audio_token": "<|endoftext11|>",
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {
+    "audio_token": "<|endoftext11|>",
+    "image_token": "<|endoftext10|>"
+  },
+  "image_token": "<|endoftext10|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Phi4MultimodalProcessor",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

vision-lora/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "model.layers.\\d+.((self_attn.(qkv|o)_proj)|(mlp.(gate_up|down)_proj))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

vision-lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76facf464ca0246e9f5dc409520e83764e0b73fa66fdb561526e064133728f8a
+size 738228552