add segment_emb

config.json

@@ -10,7 +10,7 @@
     "activation_function": "gelu",
     "add_cross_attention": false,
     "architectures": null,
-    "attention_dropout": 0.1,
+    "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,
     "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,
@@ -44,51 +42,39 @@
     "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,
-    "_attn_implementation": "flash_attention_2",
     "vocab_size": 108481
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.42.0.dev0",
   "vision_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
-    "_attn_implementation": "flash_attention_2",
     "architectures": null,
     "attention_dropout": 0.0,
     "bad_words_ids": null,
@@ -116,14 +102,13 @@
       "1": "LABEL_1"
     },
     "initializer_factor": 1.0,
-    "initializer_range": 0.02,
+    "initializer_range": 1e-10,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_bias": false,
     "layer_norm_eps": 1e-06,
     "length_penalty": 1.0,
     "max_length": 4096,
@@ -133,7 +118,6 @@
     "num_attention_heads": 24,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_channels": 3,
     "num_hidden_layers": 18,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -141,10 +125,8 @@
     "output_scores": false,
     "pad_token_id": null,
     "patch_embed_hidden_size": 768,
-    "patch_size": 16,
     "prefix": null,
     "problem_type": null,
-    "projection_dim": 768,
     "pruned_heads": {},
     "relative_attention_max_distance": 128,
     "relative_attention_num_buckets": 32,

generation_config.json

@@ -1,8 +1,9 @@
 {
-  "_from_model_config": true,
+  "_from_model_config": false,
   "bos_token_id": 0,
   "eos_token_id": 2,
-  "no_repeat_ngram_size": 3,
   "pad_token_id": 1,
-  "transformers_version": "4.40.0.dev0"
+  "transformers_version": "4.42.0.dev0",
+  "num_beam" : 1,
+  "do_sample": false
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8968c79dd845b0b139553ee156b562cb150ae2ca64a0936d68909e15f9bf51
-size 4995239744
+oid sha256:e4be3da9ff4d8a8a564e8605a914a12f5f8b38ac5927a042c1a161e86d603e42
+size 4995252144

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5498572800
+    "total_size": 5498585088
   },
   "weight_map": {
     "image_to_text_projection.dense.bias": "model-00002-of-00002.safetensors",
@@ -449,6 +449,7 @@
     "text_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "text_model.model.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
     "text_model.model.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.segment_emb.weight": "model-00001-of-00002.safetensors",
     "vision_model.embeddings.column_embedder.weight": "model-00001-of-00002.safetensors",
     "vision_model.embeddings.patch_projection.bias": "model-00001-of-00002.safetensors",
     "vision_model.embeddings.patch_projection.weight": "model-00001-of-00002.safetensors",