Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,10 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{% if t2i_generate %}<|im_start|>system
+You are a helpful image generator.<|im_end|>
+{% else %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'image_gen' or 'image_gen' in content %}<|gen_placeholder|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% if t2i_generate %}<|image start|>{{ ar_width }}*{{ ar_height }}<|image token|>{% endif %}
+{% endif %}

config.json

@@ -0,0 +1,299 @@
+{
+  "architectures": [
+    "Mammothmoda2Model"
+  ],
+  "bos_token_id": 152068,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "gen_axes_dim_rope": [
+    40,
+    40,
+    40
+  ],
+  "gen_axes_lens": [
+    10000,
+    10000,
+    10000
+  ],
+  "gen_condition_layer_merger": "pooling",
+  "gen_condition_layers": [
+    -2,
+    -5,
+    -8,
+    -11,
+    -14,
+    -17
+  ],
+  "gen_condition_mode": "text_image",
+  "gen_dit_config": {
+    "_class_name": "OmniGen2Transformer2DModel",
+    "_diffusers_version": "0.33.1",
+    "axes_dim_rope": [
+      40,
+      40,
+      40
+    ],
+    "axes_lens": [
+      1024,
+      1664,
+      1664
+    ],
+    "ffn_dim_multiplier": null,
+    "hidden_size": 2520,
+    "in_channels": 16,
+    "multiple_of": 256,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 21,
+    "num_kv_heads": 7,
+    "num_layers": 16,
+    "num_refiner_layers": 2,
+    "out_channels": null,
+    "patch_size": 2,
+    "text_feat_dim": 4096,
+    "timestep_scale": 1000.0
+  },
+  "gen_image_condition_refiner_config": {
+    "num_layers": 2,
+    "num_queries": 64
+  },
+  "gen_text_condition_max_seq_len": 512,
+  "gen_text_condition_with_answer": false,
+  "gen_transport_config": {
+    "do_shift": true,
+    "seq_len": 4096,
+    "snr_type": "lognorm"
+  },
+  "gen_vae_config": {
+    "_class_name": "AutoencoderKL",
+    "_diffusers_version": "0.30.0.dev0",
+    "_name_or_path": "../checkpoints/flux-dev",
+    "act_fn": "silu",
+    "block_out_channels": [
+      128,
+      256,
+      512,
+      512
+    ],
+    "down_block_types": [
+      "DownEncoderBlock2D",
+      "DownEncoderBlock2D",
+      "DownEncoderBlock2D",
+      "DownEncoderBlock2D"
+    ],
+    "force_upcast": true,
+    "in_channels": 3,
+    "latent_channels": 16,
+    "latents_mean": null,
+    "latents_std": null,
+    "layers_per_block": 2,
+    "mid_block_add_attention": true,
+    "norm_num_groups": 32,
+    "out_channels": 3,
+    "sample_size": 1024,
+    "scaling_factor": 0.3611,
+    "shift_factor": 0.1159,
+    "up_block_types": [
+      "UpDecoderBlock2D",
+      "UpDecoderBlock2D",
+      "UpDecoderBlock2D",
+      "UpDecoderBlock2D"
+    ],
+    "use_post_quant_conv": false,
+    "use_quant_conv": false
+  },
+  "initializer_range": 0.02,
+  "llm_config": {
+    "dtype": "bfloat16",
+    "extra_gen_vocab": true,
+    "gen_vocab_size": 32800,
+    "gen_vocab_start_index": 152064,
+    "image_token_id": 151655,
+    "model_type": "mammothmoda2_qwen3_vl",
+    "moe_type": "ffn-18:36",
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": 151643,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": "float32",
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": 151645,
+      "exponential_decay_length_penalty": null,
+      "extra_gen_vocab": true,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "gen_vocab_size": 32800,
+      "gen_vocab_start_index": 152064,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 4096,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 12288,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 262144,
+      "min_length": 0,
+      "model_type": "mammothmoda2_qwen3_vl_text",
+      "moe_type": "ffn-18:36",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 32,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 36,
+      "num_key_value_heads": 8,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": {
+        "mrope_interleaved": true,
+        "mrope_section": [
+          24,
+          20,
+          20
+        ],
+        "rope_type": "default"
+      },
+      "rope_theta": 5000000,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "unpack_forward": true,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "vocab_size": 151936
+    },
+    "unpack_forward": true,
+    "use_cache": true,
+    "video_token_id": 151656,
+    "vision_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "deepstack_visual_indexes": [
+        8,
+        16,
+        24
+      ],
+      "depth": 27,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": null,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 1152,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "in_channels": 3,
+      "initializer_range": 0.02,
+      "intermediate_size": 4304,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "mammothmoda2_qwen3_vl",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_heads": 16,
+      "num_position_embeddings": 2304,
+      "num_return_sequences": 1,
+      "out_hidden_size": 4096,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 16,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "spatial_merge_size": 2,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "temporal_patch_size": 2,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652
+  },
+  "llm_moe_init_gen_from_und": true,
+  "llm_pretrained_path": null,
+  "model_type": "mammothmoda2",
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.1",
+  "unpack_forward": true,
+  "verbose_interval": 200,
+  "vis_freeze": true
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7c63921c580ad595a03210c7836384284ea7206b0bf4f93024d9714fa96576
+size 4951322392

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab2340d41f27622955e9861d19418ddabe0b93cee069fbec629c8708f3207ee
+size 4999824288

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338579b8ffe1fba630de4a22c630befe8320dd145d65794313134635da73b63e
+size 4832050304

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2506dd507f5c96f248e057f249a584aa4ee504b88b73e25b73d508c1013dc8
+size 4832050344

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73a415edaf4f5485fcb4c818e16daff55ea2f211c42c66af0b66986700b27c8
+size 4932609376

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a895c562d6c11834e4eb698995593a96b57c29c4cc99e49a68f65378ca18e818
+size 4899089720

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4cb9918ad08ab7421f86917b6d2d01f0d8d059ac9a1229f1c797f898c9154e6
+size 4932609376

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fab1a0ff7409cb9ed4815f9fa378d8eab47a5622d1cb219dc0f88b8ccfe757
+size 4899089712

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c262fea7aa9a26459b738217a63426eaaee0161d9a44114c1dce449d9c415cd
+size 4801551272

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2800fc1384ff335110aa69afa9b0585ab0bb796c6d9786954cee0b6a23e64597
+size 4961994348

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7924b8497c8498a04165595b517ac917243bd343158385101ff37eac166e79d
+size 2013849880

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+    "min_pixels": 65536,
+    "max_pixels": 2097152,
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "processor_class": "Mammothmoda2Processor"
+}

t2i_generation_config.json

@@ -0,0 +1,18 @@
+{
+    "num_beams": 1,
+    "do_sample": true,
+    "top_p": 1.0,
+    "top_k": 2048,
+    "temperature": 1.0,
+    "repetition_penalty": 1.0,
+    "max_new_tokens": 1000,
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "eol_token_id": 152064,
+    "visual_token_start_id": 152072,
+    "visual_token_end_id": 168456
+}

und_generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 1000,
+  "pad_token_id": 151643,
+  "temperature": null,
+  "top_p": null,
+  "transformers_version": "4.57.1"
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}