Upload Florence2ForConditionalGeneration

config.json

@@ -3,8 +3,8 @@
     "Florence2ForConditionalGeneration"
   ],
   "auto_map": {
-    "AutoConfig": "microsoft/Florence-2-base-ft--configuration_florence2.Florence2Config",
-    "AutoModelForCausalLM": "microsoft/Florence-2-base-ft--modeling_florence2.Florence2ForConditionalGeneration"
+    "AutoConfig": "microsoft/Florence-2-large-ft--configuration_florence2.Florence2Config",
+    "AutoModelForCausalLM": "microsoft/Florence-2-large-ft--modeling_florence2.Florence2ForConditionalGeneration"
   },
   "bos_token_id": 0,
   "eos_token_id": 2,
@@ -12,7 +12,7 @@
   "is_encoder_decoder": true,
   "model_type": "florence2",
   "pad_token_id": 1,
-  "projection_dim": 768,
+  "projection_dim": 1024,
   "text_config": {
     "_attn_implementation_autoset": true,
     "_name_or_path": "",
@@ -30,20 +30,20 @@
     "classif_dropout": 0.1,
     "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
-    "d_model": 768,
-    "decoder_attention_heads": 12,
-    "decoder_ffn_dim": 3072,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
     "decoder_layerdrop": 0.0,
-    "decoder_layers": 6,
+    "decoder_layers": 12,
     "decoder_start_token_id": 2,
     "diversity_penalty": 0.0,
     "do_sample": false,
     "dropout": 0.1,
     "early_stopping": true,
-    "encoder_attention_heads": 12,
-    "encoder_ffn_dim": 3072,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
     "encoder_layerdrop": 0.0,
-    "encoder_layers": 6,
+    "encoder_layers": 12,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 2,
     "exponential_decay_length_penalty": null,
@@ -73,7 +73,7 @@
     "normalize_before": false,
     "num_beam_groups": 1,
     "num_beams": 3,
-    "num_hidden_layers": 6,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -124,10 +124,10 @@
       1
     ],
     "dim_embed": [
-      128,
       256,
       512,
-      1024
+      1024,
+      2048
     ],
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -161,21 +161,21 @@
     "length_penalty": 1.0,
     "max_length": 20,
     "min_length": 0,
-    "model_type": "davit",
+    "model_type": "",
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_groups": [
-      4,
       8,
       16,
-      32
+      32,
+      64
     ],
     "num_heads": [
-      4,
       8,
       16,
-      32
+      32,
+      64
     ],
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -208,7 +208,7 @@
     ],
     "prefix": null,
     "problem_type": null,
-    "projection_dim": 768,
+    "projection_dim": 1024,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,

generation_config.json

@@ -1,13 +1,4 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "no_repeat_ngram_size": 3,
   "num_beams": 3,
-  "pad_token_id": 1,
   "transformers_version": "4.51.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f39e229690389a7e392e889e167c0f41d618515f6dd00bc0ce31eb72e93f39
-size 1083916964
+oid sha256:973040590566ca14d94f4539de852127c55bfe2b90d175938760ec0cba34d6a3
+size 3291921348