Upload 9 files

qwen2/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

qwen2/config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "/mnt/workspace/lr/workspace/LLaVA_Her/checkpoints/openomni_stage3_qwen_3/checkpoint-20900",
+  "architectures": [
+    "LlavaHerQwen2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "ctc_decoder_config": "(2,896,32,11008)",
+  "ctc_loss_weight": 1,
+  "ctc_upsample_factor": 12,
+  "eos_token_id": 151645,
+  "freeze_mm_mlp_adapter": true,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_aspect_ratio": "anyres",
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mlp_bias": false,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": 2e-06,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "/mnt/workspace/lr/datasets/checkpoints/openai/clip-vit-large-patch14-336",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llava_her_qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "speech_encoder": "/mnt/workspace/lr/datasets/checkpoints/llava_her_pretrained/large-v3.pt",
+  "speech_encoder_ds_rate": 5,
+  "speech_encoder_hidden_size": 1280,
+  "speech_encoder_type": "whisper",
+  "speech_generator_type": "ar",
+  "speech_projector_type": "linear",
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 8196,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_mm_vision_tower": false,
+  "unit_vocab_size": 16384,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.43.4"
+}

qwen2/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen2/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 8196,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06f11ba747f49f1fa31c1f32bfecb9690959b617bb96f1f066aefd626a663e3
+size 7352