Upload 3 files

config.json

@@ -0,0 +1,225 @@
+{
+  "acoustic_connector_config": {},
+  "adapter_inner_dim": 512,
+  "architectures": [
+    "DIFFAModel"
+  ],
+  "conv_kernel_sizes": "5,5,5",
+  "llm_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "/path/to/models/LLaDA-8B-Instruct",
+    "activation_type": "silu",
+    "add_cross_attention": false,
+    "alibi": false,
+    "alibi_bias_max": 8.0,
+    "architectures": [
+      "LLaDAModelLM"
+    ],
+    "attention_dropout": 0.0,
+    "attention_layer_norm": false,
+    "attention_layer_norm_with_affine": true,
+    "auto_map": {
+      "AutoConfig": "configuration_llada.LLaDAConfig",
+      "AutoModel": "modeling_llada.LLaDAModelLM",
+      "AutoModelForCausalLM": "modeling_llada.LLaDAModelLM"
+    },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bias_for_layer_norm": false,
+    "block_group_size": 1,
+    "block_type": "llama",
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "d_model": 4096,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embedding_dropout": 0.0,
+    "embedding_size": 126464,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 126081,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "flash_attention": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "include_bias": false,
+    "include_qkv_bias": false,
+    "init_cutoff_factor": null,
+    "init_device": "meta",
+    "init_fn": "mitchell",
+    "init_std": 0.02,
+    "input_emb_norm": false,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_type": "rms",
+    "layer_norm_with_affine": true,
+    "length_penalty": 1.0,
+    "mask_token_id": 126336,
+    "max_length": 20,
+    "max_sequence_length": 4096,
+    "min_length": 0,
+    "mlp_hidden_size": 12288,
+    "mlp_ratio": 4,
+    "model_type": "llada",
+    "multi_query_attention": null,
+    "n_heads": 32,
+    "n_kv_heads": 32,
+    "n_layers": 32,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 126081,
+    "precision": "amp_bf16",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "residual_dropout": 0.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope": true,
+    "rope_full_precision": true,
+    "rope_theta": 500000.0,
+    "scale_logits": false,
+    "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": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.49.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "vocab_size": 126464,
+    "weight_tying": false
+  },
+  "prompt_size": 64,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "whisper_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "openai/whisper-large-v3",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": false,
+    "apply_spec_augment": false,
+    "architectures": [
+      "WhisperForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": [
+      220,
+      50257
+    ],
+    "bos_token_id": 50257,
+    "chunk_size_feed_forward": 0,
+    "classifier_proj_size": 256,
+    "cross_attention_hidden_size": null,
+    "d_model": 1280,
+    "decoder_attention_heads": 20,
+    "decoder_ffn_dim": 5120,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 32,
+    "decoder_start_token_id": 50258,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_attention_heads": 20,
+    "encoder_ffn_dim": 5120,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 32,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50257,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.05,
+    "max_length": 448,
+    "max_source_positions": 1500,
+    "max_target_positions": 448,
+    "median_filter_width": 7,
+    "min_length": 0,
+    "model_type": "whisper",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_mel_bins": 128,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 50256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "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": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float16",
+    "torchscript": false,
+    "transformers_version": "4.49.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 51866
+  },
+  "whisper_model_id": "openai/whisper-large-v3"
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.49.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7053e74ffc9631fffa321ff0f3a26a009b20aa95fecf173631bd79947f2818
+size 396253779