Upload MllamaForConditionalGeneration

config.json

@@ -1,42 +1,10 @@
 {
+  "_name_or_path": "meta-llama/Llama-3.2-90B-Vision",
   "architectures": [
-    "MllamaForCausalLM"
+    "MllamaForConditionalGeneration"
   ],
-  "bos_token_id": 128000,
-  "cross_attention_layers": [
-    3,
-    8,
-    13,
-    18,
-    23,
-    28,
-    33,
-    38,
-    43,
-    48,
-    53,
-    58,
-    63,
-    68,
-    73,
-    78,
-    83,
-    88,
-    93,
-    98
-  ],
-  "dropout": 0,
-  "eos_token_id": 128001,
-  "hidden_act": "silu",
-  "hidden_size": 8192,
-  "initializer_range": 0.02,
-  "intermediate_size": 28672,
-  "max_position_embeddings": 131072,
-  "model_type": "mllama_text_model",
-  "num_attention_heads": 64,
-  "num_hidden_layers": 100,
-  "num_key_value_heads": 8,
-  "pad_token_id": 128004,
+  "image_token_index": 128256,
+  "model_type": "mllama",
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
@@ -52,18 +20,228 @@
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "cross_attention_layers": [
+      3,
+      8,
+      13,
+      18,
+      23,
+      28,
+      33,
+      38,
+      43,
+      48,
+      53,
+      58,
+      63,
+      68,
+      73,
+      78,
+      83,
+      88,
+      93,
+      98
+    ],
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 128001,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 131072,
+    "min_length": 0,
+    "model_type": "mllama_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 64,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 100,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 128004,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "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": 500000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128256
   },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.0.dev0",
-  "use_cache": true,
-  "vocab_size": 128256
+  "transformers_version": "4.45.0",
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_heads": 16,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 560,
+    "initializer_range": 0.02,
+    "intermediate_layers_indices": [
+      3,
+      7,
+      15,
+      23,
+      30
+    ],
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_num_tiles": 4,
+    "min_length": 0,
+    "model_type": "mllama_vision_model",
+    "no_repeat_ngram_size": 0,
+    "norm_eps": 1e-05,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_global_layers": 8,
+    "num_hidden_layers": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "supported_aspect_ratios": [
+      [
+        1,
+        1
+      ],
+      [
+        1,
+        2
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        1,
+        4
+      ],
+      [
+        2,
+        1
+      ],
+      [
+        2,
+        2
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        4,
+        1
+      ]
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_output_dim": 7680
+  }
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 128000,
   "eos_token_id": 128001,
   "pad_token_id": 128004,
-  "transformers_version": "4.46.0.dev0"
+  "transformers_version": "4.45.0"
 }

model-00001-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774a2c2132673d5fff22bb1d4d0f2a99b79700e4bd3ca0cc302ae0f4e4e4314c
-size 4949214341
+oid sha256:650c83289f75bc2a94392020f4e08af0d7506060e5bce93cf44786582dce0636
+size 4947107668

model-00002-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781d95215ed339242a2f234380a4c419f8012968906b6d18c4acc5cfb1e27093
-size 4977056847
+oid sha256:18e5c46b8eedcee0601cb9d7e82ee5e7cba955320f62a422c66bdc88069601bf
+size 4977064275

model-00003-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290f0c8c9a3c9e16956676d3ce7eb0528405c745d7ce24032adf1634ed5adf93
-size 4977090920
+oid sha256:f0ce49d0d5e5a39cd48319d7342dc0a9696502635e49f6764dcac17fced44b66
+size 4977064457

model-00004-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ca25c9b536aced3325b890c3a3ab6ef645e196bb9bd7371122c3db62b03cc8
-size 4933788727
+oid sha256:fe3877119333def8ac635bda019a948d71dd6bea414e8b762896a426adc66e28
+size 4977098481

model-00005-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:493d614295ff52254bc18c164258e25093667adf7e243ecaa49a46ca847f7dba
-size 4977057042
+oid sha256:e25f18c284437a34d7f23009810241f5206a122d4c9a6b84b6c077eafce4b639
+size 4933796472

model-00006-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7fb6dc2ede8961d6144ad5a9914da8b88da7be122090cc6407b281f725ada97
-size 4977056984
+oid sha256:76839275d021157fac0cabbd9268a967d773cbd1812f373868df191d61fe145a
+size 4977064511

model-00007-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0dd28a2d392a138de23ad9caa3c55be064bbbc8daa70beefdf01d69f4858150
-size 4977090913
+oid sha256:04baa35520390768a11cc24bcef62e2c09feee44db3e07bb5a39b304b9ebd87c
+size 4977064451

model-00008-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6232e968997b9b374c1eef945c34d056d2c4bb2a1f91129e7375296051cb7df
-size 4933788729
+oid sha256:5db190966344fabd62fbc653d53aa6150bc2d4b9d2f7da7f376b15520c09c290
+size 4977098474

model-00009-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ed7f9dd9d7c1dc8b45a75a29d70e18d690e41683c78d7b1b77536e05f582c0
-size 4977057020
+oid sha256:f07a2eda5aa9585bac1498cde97455d60c82e020beeae95908b8971d0e546719
+size 4933796461

model-00010-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e836bbf317955e75261bd18af3e5ade3a0583a77ec11eb95923ee3a9b7c34f
-size 3668068871
+oid sha256:7d49c1260afdadaaa9c457099340ebe47dece62a0ff5c1eb4f1b257991b80818
+size 4263159968