Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "MFuyu/mfuyu_llava_8192_480p",
+  "architectures": [
+    "MFuyuForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 71013,
+  "hidden_act": "relu2",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "image_size": 300,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 16384,
+  "model_type": "fuyu",
+  "num_attention_heads": 64,
+  "num_channels": 3,
+  "num_hidden_layers": 36,
+  "partial_rotary_factor": 0.5,
+  "patch_size": 30,
+  "qk_layernorm": true,
+  "rope_scaling": null,
+  "rope_theta": 25000.0,
+  "text_config": {
+    "model_type": "persimmon",
+    "vocab_size": 262146
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 262146
+}

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": 0.5,
+  "image_processor_type": "FuyuImageProcessor",
+  "image_std": 0.5,
+  "padding_mode": "constant",
+  "padding_value": 1.0,
+  "patch_size": {
+    "height": 30,
+    "width": 30
+  },
+  "processor_class": "MFuyuProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 480,
+    "width": 660
+  },
+  "target_height": 1080,
+  "target_width": 1920
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "|IMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "|ENDOFIMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "|ENDOFTEXT|",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "|ENDOFTEXT|",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6db0b2169918176bbed18b26e73d12d8c09dfa0ed8b248d2c054e7df9f5cfce
+size 16454942

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71013": {
+      "content": "|ENDOFTEXT|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "262144": {
+      "content": "|IMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "262145": {
+      "content": "|ENDOFIMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "|IMAGE|",
+    "|ENDOFIMAGE|"
+  ],
+  "bos_token": "|ENDOFTEXT|",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "|ENDOFTEXT|",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "processor_class": "MFuyuProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dfbf0711f6d078c63c8424d99de5e533dd05a74f8ff0331e3ec54eda4f01f9
+size 6008