Upload mllm/config.json with huggingface_hub

mllm/config.json

@@ -0,0 +1,210 @@
+{
+  "architectures": [
+    "BailingMM2NativeForConditionalGeneration"
+  ],
+  "audio_config": null,
+  "llm_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "BailingMoeV2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "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,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embedding_dropout": 0.0,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 156895,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "first_k_dense_replace": 1,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_end_token": 157159,
+    "image_patch_token": 157157,
+    "image_start_token": 157158,
+    "video_end_token": 157161,
+    "video_patch_token": 157175,
+    "video_start_token": 157160,
+    "initializer_range": 0.006,
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "min_length": 0,
+    "model_type": "bailing_moe_v2",
+    "moe_intermediate_size": 512,
+    "moe_router_topk_scaling_factor": 2.5,
+    "n_group": 8,
+    "no_repeat_ngram_size": 0,
+    "norm_head": false,
+    "norm_softmax": false,
+    "norm_topk_prob": true,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_experts": 256,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 20,
+    "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "num_shared_experts": 1,
+    "output_attentions": false,
+    "output_dropout": 0.0,
+    "output_hidden_states": false,
+    "output_router_logits": false,
+    "output_scores": false,
+    "pad_token_id": 156892,
+    "partial_rotary_factor": 0.5,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "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": {
+      "factor": null,
+      "type": "video_rope"
+    },
+    "rope_theta": 600000,
+    "routed_scaling_factor": 2.5,
+    "router_type": "MultiRouter",
+    "sep_token_id": null,
+    "sliding_window": 4096,
+    "spatial_merge_size": 2,
+    "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,
+    "tokens_per_second": 2,
+    "top_k": 50,
+    "top_p": 1.0,
+    "topk_group": 4,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_bias": false,
+    "use_cache": true,
+    "use_expert_bias": true,
+    "use_qkv_bias": false,
+    "use_sliding_window": false,
+    "vocab_size": 157184
+  },
+  "mlp_depth": 2,
+  "model_type": "bailingmm_moe_v2_lite",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0.dev0",
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2_5_VisionTransformer"
+    ],
+    "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,
+    "depth": 32,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "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,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3456,
+    "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": "qwen2_5_vit",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_heads": 16,
+    "num_return_sequences": 1,
+    "out_hidden_size": 8192,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "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,
+    "spatial_patch_size": 14,
+    "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,
+    "tokens_per_second": 2,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "window_size": 112
+  }
+}