update after integration

config.json

@@ -10,7 +10,7 @@
     "activation_function": "gelu",
     "add_cross_attention": false,
     "architectures": null,
-    "attention_dropout": 0,
+    "attention_dropout": 0.0,
     "attention_heads": 16,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
@@ -18,12 +18,10 @@
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.1,
+    "dropout": 0,
     "early_stopping": false,
     "embed_dim": 1536,
-    "encoder_no_repeat_ngram_size": 0,
+    "pad_token_id": 1,
     "eos_token_id": 2,
     "exponential_decay_length_penalty": null,
     "ffn_dim": 6144,
@@ -44,46 +42,36 @@
     "layer_norm_eps": 1e-05,
     "layerdrop": 0.0,
     "layers": 24,
-    "length_penalty": 1.0,
     "max_length": 20,
     "max_position_embeddings": 4096,
     "min_length": 0,
     "model_type": "kosmos_2_5_text_model",
-    "no_repeat_ngram_size": 3,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 1,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
     "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
     "scale_embedding": true,
     "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": true,
     "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
     "vocab_size": 108481
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
+  "transformers_version": "4.42.0.dev0",
   "vision_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -94,8 +82,8 @@
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
-    "d_ff": 3968,
-    "d_kv": 64,
+    "intermediate_size": 3968,
+    "head_dim": 64,
     "decoder_start_token_id": null,
     "dense_act_fn": "gelu_new",
     "diversity_penalty": 0.0,
@@ -123,7 +111,7 @@
     },
     "layer_norm_eps": 1e-06,
     "length_penalty": 1.0,
-    "max_length": 20,
+    "max_length": 4096,
     "min_length": 0,
     "model_type": "kosmos_2_5_vision_model",
     "no_repeat_ngram_size": 0,
@@ -140,14 +128,12 @@
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
-    "relative_attention_max_distance": 128,
-    "relative_attention_num_buckets": 32,
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
     "sep_token_id": null,
-    "seq_len": 4096,
+    "max_num_patches": 4096,
     "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
@@ -162,4 +148,4 @@
     "typical_p": 1.0,
     "use_bfloat16": false
   }
-}
+}

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "no_repeat_ngram_size": 3,
   "pad_token_id": 1,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.43.3",
 }

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<image>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "</image>",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<s>",
+  "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
+  }
+}