Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloomz-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "transformers_version": "4.33.0.dev0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.33.0.dev0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fb71c5ded414ab8f1cbd7d5746d6f52d8e9083205bb346528ca536ff80c849
+size 708465

onnx/decoder_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f635b89653beb3954b0264474eddfbedf263eb0182b6aee0d8d753cf8e2d4dc
+size 2236858368

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014c9564cd5e7b1d825a47c4cd12dba3b082031a16409d4daf05140b3e328b4f
+size 1399544

onnx/decoder_model_merged.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f635b89653beb3954b0264474eddfbedf263eb0182b6aee0d8d753cf8e2d4dc
+size 2236858368

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca26a9704720663a3bd8713596d6e95023d5e320032ce717cfbf990da827345
+size 562242269

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3a593ea5f6fe47aac5447109658d113489cef68c1448721b541c940965ff54
+size 561214691

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e90698757af8933ef57252d2a16b3bb48752b8d7d0fa6cfa01c14b92b52d75
+size 714978

onnx/decoder_with_past_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f635b89653beb3954b0264474eddfbedf263eb0182b6aee0d8d753cf8e2d4dc
+size 2236858368

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d1b23f04c47b265bc4e8d335805f2b1844853a84c51c637d3f72a5a20a2f14
+size 561216819

quantize_config.json

@@ -0,0 +1,104 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Sub",
+                "MatMul",
+                "CumSum",
+                "Div",
+                "Constant",
+                "ReduceMean",
+                "ScatterND",
+                "Gather",
+                "Equal",
+                "Shape",
+                "Slice",
+                "Concat",
+                "Where",
+                "ConstantOfShape",
+                "Cast",
+                "Less",
+                "Not",
+                "Unsqueeze",
+                "Mul",
+                "Reshape",
+                "Tanh",
+                "Expand",
+                "Add",
+                "Range",
+                "Transpose",
+                "Sqrt",
+                "Softmax",
+                "Pow",
+                "Or"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Sub",
+                "MatMul",
+                "CumSum",
+                "Div",
+                "Constant",
+                "ReduceMean",
+                "ScatterND",
+                "Gather",
+                "Equal",
+                "Shape",
+                "Slice",
+                "Concat",
+                "Where",
+                "ConstantOfShape",
+                "Cast",
+                "Less",
+                "If",
+                "Not",
+                "Unsqueeze",
+                "Mul",
+                "Reshape",
+                "Tanh",
+                "Expand",
+                "Add",
+                "Range",
+                "Transpose",
+                "Sqrt",
+                "Softmax",
+                "Pow",
+                "Or"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Sub",
+                "MatMul",
+                "CumSum",
+                "Div",
+                "Constant",
+                "ReduceMean",
+                "Gather",
+                "Equal",
+                "Shape",
+                "Concat",
+                "Where",
+                "ConstantOfShape",
+                "Cast",
+                "Not",
+                "Unsqueeze",
+                "Mul",
+                "Reshape",
+                "Tanh",
+                "Expand",
+                "Add",
+                "Transpose",
+                "Sqrt",
+                "Softmax",
+                "Pow"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
+size 14500471

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}