flan-base-retrain

README.md

@@ -1,7 +0,0 @@
----
-library_name: transformers.js
----
-
-https://huggingface.co/MBZUAI/LaMini-Flan-T5-783M with ONNX weights to be compatible with Transformers.js.
-
-Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "MBZUAI/LaMini-Flan-T5-783M",
+  "_name_or_path": "google/flan-t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2816,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -18,15 +18,44 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
   "tie_word_embeddings": false,
-  "transformers_version": "4.34.0.dev0",
+  "transformers_version": "4.33.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.34.0.dev0"
+  "transformers_version": "4.33.2"
 }

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2dc690641be4851a21e4040c1d8e74c7d51486761730947de96df254bbd1c0
+size 650848961

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0f2970b86081611577dfba0fbd41a4237546c1bd9104b4aeefb1497d0a6626
+size 651182887

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b47d2f266e175d42559a29c6330483769baca5b82042814e981402b49d4efcb
+size 594197309

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c438df6ed8f9479f3b8ce43d4903cb4817d7c1e0d5c47b86a7a2ca9de621c9
+size 438697388

quantize_config.json

@@ -1,139 +0,0 @@
-{
-    "per_channel": true,
-    "reduce_range": true,
-    "per_model_config": {
-        "decoder_model": {
-            "op_types": [
-                "Add",
-                "Less",
-                "ConstantOfShape",
-                "Mul",
-                "Pow",
-                "Gather",
-                "Shape",
-                "ReduceMean",
-                "MatMul",
-                "Range",
-                "Transpose",
-                "Neg",
-                "Expand",
-                "Sqrt",
-                "Min",
-                "Unsqueeze",
-                "Where",
-                "Div",
-                "Tile",
-                "Log",
-                "Concat",
-                "Cast",
-                "LessOrEqual",
-                "Reshape",
-                "Sub",
-                "Softmax",
-                "Tanh",
-                "Constant"
-            ],
-            "weight_type": "QInt8"
-        },
-        "encoder_model": {
-            "op_types": [
-                "Add",
-                "Abs",
-                "Less",
-                "ConstantOfShape",
-                "Mul",
-                "Pow",
-                "Gather",
-                "Shape",
-                "ReduceMean",
-                "MatMul",
-                "Range",
-                "Transpose",
-                "Sqrt",
-                "Min",
-                "Unsqueeze",
-                "Where",
-                "Div",
-                "Greater",
-                "Log",
-                "Concat",
-                "Cast",
-                "Reshape",
-                "Sub",
-                "Softmax",
-                "Tanh",
-                "Constant"
-            ],
-            "weight_type": "QInt8"
-        },
-        "decoder_model_merged": {
-            "op_types": [
-                "If",
-                "Add",
-                "Less",
-                "ConstantOfShape",
-                "Mul",
-                "Slice",
-                "Pow",
-                "Gather",
-                "Shape",
-                "ReduceMean",
-                "MatMul",
-                "Range",
-                "Transpose",
-                "Neg",
-                "Expand",
-                "Sqrt",
-                "Min",
-                "Unsqueeze",
-                "Where",
-                "Div",
-                "Tile",
-                "Log",
-                "Concat",
-                "Cast",
-                "LessOrEqual",
-                "Reshape",
-                "Sub",
-                "Softmax",
-                "Tanh",
-                "Constant"
-            ],
-            "weight_type": "QInt8"
-        },
-        "decoder_with_past_model": {
-            "op_types": [
-                "Add",
-                "Less",
-                "ConstantOfShape",
-                "Mul",
-                "Slice",
-                "Pow",
-                "Gather",
-                "Shape",
-                "ReduceMean",
-                "MatMul",
-                "Range",
-                "Transpose",
-                "Neg",
-                "Expand",
-                "Sqrt",
-                "Min",
-                "Unsqueeze",
-                "Where",
-                "Div",
-                "Tile",
-                "Log",
-                "Concat",
-                "Cast",
-                "LessOrEqual",
-                "Reshape",
-                "Sub",
-                "Softmax",
-                "Tanh",
-                "Constant"
-            ],
-            "weight_type": "QInt8"
-        }
-    }
-}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656