Upload InstructBlipForConditionalGeneration

config.json

@@ -82,7 +82,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.30.0.dev0",
+    "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 30523
@@ -193,7 +193,7 @@
     "top_p": 1.0,
     "torch_dtype": "float32",
     "torchscript": false,
-    "transformers_version": "4.30.0.dev0",
+    "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
@@ -240,7 +240,7 @@
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-05,
+    "layer_norm_eps": 1e-06,
     "length_penalty": 1.0,
     "max_length": 20,
     "min_length": 0,
@@ -259,7 +259,6 @@
     "patch_size": 14,
     "prefix": null,
     "problem_type": null,
-    "projection_dim": 512,
     "pruned_heads": {},
     "qkv_bias": true,
     "remove_invalid_values": false,
@@ -278,7 +277,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.30.0.dev0",
+    "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false
   }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8756aca7708f1c9197f94c04ea2dc27a50040e4de85124e9366836013659fbe9
-size 9587341371
+oid sha256:df1dfe95c6345c17661be74efd2a8891a692ee8f3c71c06debaebccba6e4354d
+size 9981661575

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e652fa687e40280479a7e29d28a7a3c7ec7e6a525c4880e604294c826c32c8bd
-size 6768240895
+oid sha256:33324062656d33010bfc4a28be0ced982bbd53c9db705fcbabedd5a3f078aa6c
+size 6110728493

pytorch_model.bin.index.json

@@ -1,33 +1,33 @@
 {
   "metadata": {
-    "total_size": 16618265600
+    "total_size": 16091880448
   },
   "weight_map": {
-    "language_model.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
@@ -340,7 +340,7 @@
     "language_model.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "language_model.decoder.embed_tokens.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
     "language_model.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
     "language_model.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",