Upload madlad400-3b ONNX INT8

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+madlad400-3b-int8/tokenizer.json filter=lfs diff=lfs merge=lfs -text

madlad400-3b-int8/LICENSE

@@ -0,0 +1,16 @@
+Original model: google/madlad400-3b-mt
+License: Apache-2.0
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+Copyright 2024 Google LLC

madlad400-3b-int8/README.md

@@ -0,0 +1,39 @@
+---
+license: apache-2.0
+base_model: google/madlad400-3b-mt
+tags:
+  - translation
+  - onnx
+  - int8
+  - multilingual
+  - nobuds
+language:
+  - multilingual
+---
+
+# MADLAD-400 3B ONNX INT8
+
+INT8 quantized ONNX export of [google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt) for on-device multilingual translation.
+
+- **Parameters:** 3B (T5-based)
+- **Languages:** 450+
+- **License:** Apache 2.0
+- **Quantization:** INT8 dynamic (optimum O3)
+- **Export tool:** optimum-cli
+
+## Files
+
+- `encoder_model_quantized.onnx` — Encoder
+- `decoder_model_quantized.onnx` — Decoder (initial)
+- `decoder_with_past_model_quantized.onnx` — Decoder (with past key-values)
+- `spiece.model` — SentencePiece tokenizer (T5)
+- `tokenizer.json` — Fast tokenizer config
+
+## Language prefix
+
+MADLAD-400 uses target-language prefixes: `<2xx>` where `xx` is the language code.
+Example: `<2de> Hello world` translates to German.
+
+## Note
+
+At ~3 GB INT8, this model is large for mobile deployment. Consider M2M-100 418M (~630 MB) for resource-constrained devices.

madlad400-3b-int8/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 8192,
+  "d_kv": 128,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 32,
+  "num_heads": 16,
+  "num_layers": 32,
+  "output_past": true,
+  "pad_token_id": 1,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {},
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 256000
+}

madlad400-3b-int8/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097e4f2cb191f826e9f53270ee2d721e52dcdfce03675fb1fd1ec07ba55fcac4
+size 1876592396

madlad400-3b-int8/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48dcf2742c5c1a9b01b4eed6c66412c35c7be1a6a0391f755db3c6ba4ba4865f
+size 1741384192

madlad400-3b-int8/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43b2dc0f30a25cf1fba919bf0c77dccaaf45e00cfd0dc0adfbd4d7959df0cfc
+size 1341985948

madlad400-3b-int8/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.57.6"
+}

madlad400-3b-int8/ort_config.json

@@ -0,0 +1,33 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": true,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QUInt8",
+    "weights_symmetric": true
+  },
+  "use_external_data_format": false
+}

madlad400-3b-int8/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

madlad400-3b-int8/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef11ac9a22c7503492f56d48dce53be20e339b63605983e9f27d2cd0e0f3922c
+size 4427844

madlad400-3b-int8/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f5d7dc88da0cb4bb6b7a1d9d66ee62f5bd339ef0aaaf6e89d74829df5830c0
+size 16613995

madlad400-3b-int8/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}