first commit

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "./checkpoints/qwen14b-finetune_all-3m-ocr-448-1024-zero3/checkpoint-4500",
+  "architectures": [
+    "HuazangQWenForCausalLM"
+  ],
+  "attn_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
+  },
+  "bf16": true,
+  "emb_dropout_prob": 0.0,
+  "fp16": false,
+  "fp32": false,
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 27392,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 8192,
+  "mm_hidden_size": 1024,
+  "mm_projector_lr": null,
+  "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": "./huazang_sxp/pretrain_weight/qwen_vit_448",
+  "model_type": "Huazang_Qwen",
+  "no_bias": true,
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "onnx_safe": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "scale_attn_weights": true,
+  "seq_length": 2048,
+  "softmax_in_fp32": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "QWenTokenizer",
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "tune_mm_mlp_adapter": true,
+  "use_cache": true,
+  "use_cache_kernel": false,
+  "use_cache_quantization": false,
+  "use_dynamic_ntk": true,
+  "use_flash_attn": true,
+  "use_logn_attn": true,
+  "use_mm_proj": true,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "chat_format": "chatml",
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "max_window_size": 6144,
+  "pad_token_id": 151643,
+  "top_k": 0,
+  "top_p": 0.8,
+  "transformers_version": "4.34.0"
+}

mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dde34621edf02e129ab42ccb7e7816e7b9bd02260280b9f9ab8a163fcba016a
+size 295040401

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b4c35aa4ab02144ea37fb7cc9b90178e01da6902b8b9004f501142822632bd
+size 9963536445

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8486db2d1c4adbd5b44e03eca48cd3266b26ba717aab215fb6ec21377b20cd0a
+size 9878405831

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1adf96deefa5a251afe38cd5fe07c3d14edd6d2de25526d3c58a94de6350db
+size 9980282713

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fed7074c0709dc7af38d85e468e6d8d6ad60cfdd2a9259c633a202f998bd2da
+size 2684467664

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "added_tokens_decoder": {},
+  "additional_special_tokens": [],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "QWenTokenizer",
+  "tokenizer_file": null,
+  "use_fast": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8577a1072be38aa38801cb46d1a8e8a39148a8322caad8fed0cdcb369bf21f04
+size 6139