Upload folder using huggingface_hub

cfg.json

@@ -0,0 +1 @@
+{"llm_checkpoint_path": "/gsdata/home/cyzhao/model_zoo/TinyLlama-1.1B-Chat-v1.0", "vae_checkpoint_path": "/gsdata/home/cyzhao/model_zoo/sd-vae-ft-mse", "use_iterable_dataset": false, "datasets": [{"type": "imagenet", "data_root": "/gsdata/home/wangwh/ILSVRC2012_RAW_PYTORCH/train/", "weight": 9}], "img_data_root": "/root/paddlejob/workspace/vae_features/256resolution/noflip", "load_vae_features": false, "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 %}", "tokenizer_max_length": 512, "source_max_length": 128, "llm_lr": null, "use_lr_decay": false, "warmup_iters": 500, "lr_decay_iters": 300000, "lr_decay_rate": 0.1, "loss_dict": {"loss_lm": 1.0, "loss_dit": 1.0}}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "/gsdata/home/cyzhao/model_zoo/TinyLlama-1.1B-Chat-v1.0",
+  "add_pos_embed_each_layer": false,
+  "architectures": [
+    "LlamaDitForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "decoder_t_embed": "add_before_image_tokens",
+  "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": "/gsdata/home/cyzhao/model_zoo/TinyLlama-1.1B-Chat-v1.0",
+  "add_pos_embed_each_layer": false,
+  "architectures": [
+    "LlamaDitForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "decoder_t_embed": "add_before_image_tokens",
+  "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 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.0"
+}

ema/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82d4cd654dfe8dc9f8807399f6edf2c01070db4b92d8d617671158cc534fe2f
+size 4486766733

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.0"
+}

model_args.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62322bf341582dd3d1003c67a35a66864436580439d17214ef9cbf0aefab0cbe
+size 1141

optimizer.00000-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50acfb4ab70fb5e95155b846b9999d205cf4e6ae1e1b9a6c5a0d8d0f2d79268a
+size 1121751880

optimizer.00001-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e60d44936a5fd196dcfdbc349923e78e5f86a20a8ac91606364ff1465c8009
+size 1121713228

optimizer.00002-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef8882d094d1602edab52dce99e2a1ccd5cff29afbd9623a308777e98e236cc
+size 1121693965

optimizer.00003-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42174dbe9b598e87e668e1198423950a5614dce105fefc388b1fed5bcc048509
+size 1121714982

optimizer.00004-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a01e61b8b78248103ee3dd0ebe40ce7bb186c9e878f043350a17c552b65102
+size 1121693965

optimizer.00005-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fc8327ea844e71357bcefed3b3443f361ae46f3e296410cebd79f0bbce37ab
+size 1121713228

optimizer.00006-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f4bfb2d58d98e7de516bad98e3ed8190ddd4920479d28c6e7fe09f88e474bb
+size 1121696523

optimizer.00007-of-00008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1d5431ed1b5c020278115ad166bc3cd546de567d95fbf32f1fc6c15a112654
+size 1121741785

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc69fff1129f9a35013764eb3ca9850f30ab47c6f045ef6a8876c068fc97f856
+size 4486766733

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
+}