Upload folder using huggingface_hub

cfg.json

@@ -0,0 +1 @@
+{"llm_checkpoint_path": "/root/paddlejob/workspace/box5_home/disk1/vis/songyuxin02/data/checkpoints/TinyLlama-1.1B-Chat-v1.0", "vae_checkpoint_path": "/root/paddlejob/workspace/box5_home/disk1/vis/songyuxin02/data/checkpoints/sd-vae-ft-ema", "use_iterable_dataset": true, "datasets": [{"type": "image", "data_root": "/root/paddlejob/workspace/env_run/afs_baihua/zhaochuyang/data/llmdit/hdf5_256/journeydb/", "prompt_type": "prompt", "weight": 9}, {"type": "ultrachat", "data_root": "/root/paddlejob/workspace/env_run/afs_baihua/zhaochuyang/data/llmdit/ultrachat/", "weight": 1}], "patch_size": 2, "in_channels": 4, "learn_sigma": true, "use_flash_attn": false, "use_pos_embed": true, "decoder_t_embed": "add_before_image_tokens", "use_adaln_final_layer": true, "use_bi_attn_img_tokens": true, "use_chat_template": false, "chat_template": "{%- for message in messages %}{%- if message['role'] == 'user' %}{{- bos_token + '### Human: ' + message['content'].strip() }}{%- elif message['role'] == 'assistant' %}{{- '### Assistant: ' + message['content'] + eos_token }}{%- endif %}{%- if loop.last and add_generation_prompt %}{{- '### Assistant: '}}{%- endif %}{%- endfor %}", "use_adaln": false, "add_t_embed_before_decoder": false, "tokenizer_max_length": 512, "source_max_length": 128, "llm_lr": null, "use_lr_decay": true, "warmup_iters": 500, "lr_decay_iters": 300000, "lr_decay_rate": 0.1, "loss_dict": {"loss_lm": 0.1, "loss_diffusion": 1.0}}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "monoformer_imagenet_res256",
+  "add_pos_embed_each_layer": false,
+  "architectures": [
+    "MonoFormerForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "decoder_t_embed": "adaln_before_decoder",
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_size": 256,
+  "image_token_index": 32001,
+  "in_channels": 4,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "learn_sigma": true,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "patch_size": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_max_length": 512,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "use_adaln_final_layer": true,
+  "use_bi_attn_img_tokens": true,
+  "use_cache": true,
+  "use_flash_attn": false,
+  "use_pos_embed": true,
+  "vocab_size": 32004
+}

ema/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "/root/paddlejob/workspace/env_run/afs_baihua/zhaochuyang/llmdit-results/llmdit_bs48_lr1e-4_bf16_train_mix_journeydb/checkpoint-20000",
+  "add_pos_embed_each_layer": false,
+  "architectures": [
+    "MonoFormerForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "decoder_t_embed": "adaln_before_decoder",
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_size": 256,
+  "image_token_index": 32001,
+  "in_channels": 4,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "learn_sigma": true,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "patch_size": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_max_length": 512,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "use_adaln_final_layer": true,
+  "use_bi_attn_img_tokens": true,
+  "use_cache": true,
+  "use_flash_attn": false,
+  "use_pos_embed": true,
+  "vocab_size": 32004
+}

ema/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0"
+}

ema/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99de53883cddaaaa067eae46088ef6fcf492f0c2640c69e65ab77b9fd9ea7812
+size 4486717144

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:102a66c872c37abaf1ee73196e1a90556e57e119c1e56e006d53e24e684b2693
+size 4486717144

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<PAD>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}