Upload folder using huggingface_hub

README.md

@@ -14,7 +14,7 @@ This is [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/Re
 Weight compression was performed using `nncf.compress_weights` with the following parameters:
 
 * mode: **int4_asym**
-* ratio: **0.8**
+* ratio: **1**
 * group_size: **128**
 
 For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).
@@ -24,11 +24,10 @@ For more information on quantization, check the [OpenVINO model optimization gui
 
 The provided OpenVINO™ IR model is compatible with:
 
-* OpenVINO version 2024.2.0 and higher
-* Optimum Intel 1.19.0 and higher
-
-## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
+* OpenVINO version 2024.4.0 and higher
+* Optimum Intel 1.20.0 and higher
 
+## Running Model Inference
 
 1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
 
@@ -55,40 +54,9 @@ print(text)
 
 For more examples and possible optimizations, refer to the [OpenVINO Large Language Model Inference Guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html).
 
-## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
-
-1. Install packages required for using OpenVINO GenAI.
-```
-pip install openvino-genai huggingface_hub
-```
-
-2. Download model from HuggingFace Hub
-   
-```
-import huggingface_hub as hf_hub
-
-model_id = "OpenVINO/RedPajama-INCITE-Chat-3B-v1-int4-ov"
-model_path = "RedPajama-INCITE-Chat-3B-v1-int4-ov"
-
-hf_hub.snapshot_download(model_id, local_dir=model_path)
-
-```
-
-3. Run model inference:
-
-```
-import openvino_genai as ov_genai
-
-device = "CPU"
-pipe = ov_genai.LLMPipeline(model_path, device)
-print(pipe.generate("What is OpenVINO?", max_length=200))
-```
-
-More GenAI usage examples can be found in OpenVINO GenAI library [docs](https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md) and [samples](https://github.com/openvinotoolkit/openvino.genai?tab=readme-ov-file#openvino-genai-samples)
-
 ## Limitations
 
-Check the original model card for [limitations]().
+Check the original model card for [original model card](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1) for limitations.
 
 ## Legal information
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "OpenVINO/RedPajama-INCITE-Chat-3B-v1-int4-ov",
+  "_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -18,11 +18,14 @@
   "model_type": "gpt_neox",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
+  "partial_rotary_factor": 1.0,
   "rope_scaling": null,
+  "rope_theta": 10000,
   "rotary_emb_base": 10000,
   "rotary_pct": 1.0,
   "tie_word_embeddings": false,
-  "transformers_version": "4.41.2",
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "use_parallel_residual": false,
   "vocab_size": 50432

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.45.2"
 }

openvino_config.json

@@ -0,0 +1,25 @@
+{
+  "compression": null,
+  "dtype": "int4",
+  "input_info": null,
+  "optimum_version": "1.23.1",
+  "quantization_config": {
+    "all_layers": null,
+    "bits": 4,
+    "dataset": "wikitext2",
+    "gptq": null,
+    "group_size": 128,
+    "ignored_scope": null,
+    "num_samples": null,
+    "quant_method": "default",
+    "ratio": 1.0,
+    "scale_estimation": true,
+    "sensitivity_metric": null,
+    "sym": false,
+    "tokenizer": null,
+    "trust_remote_code": true,
+    "weight_format": "int4"
+  },
+  "save_onnx_model": false,
+  "transformers_version": "4.45.2"
+}

openvino_detokenizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cc9ef2460d39577b5a80e2b379766a90187c17b436a2e530467180319bc312
-size 558446
+oid sha256:1da2b7ea623e526bc5d1b509164ae94e333c3c762fbc6d8f6e90384e6f0d6b66
+size 514079

openvino_detokenizer.xml

@@ -1,16 +1,16 @@
 <?xml version="1.0"?>
 <net name="detokenizer" version="11">
 	<layers>
-		<layer id="0" name="Parameter_458255" type="Parameter" version="opset1">
+		<layer id="0" name="Parameter_184670" type="Parameter" version="opset1">
 			<data shape="?,?" element_type="i64" />
 			<output>
-				<port id="0" precision="I64" names="Parameter_458255">
+				<port id="0" precision="I64" names="Parameter_184670">
 					<dim>-1</dim>
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="1" name="Convert_458271" type="Convert" version="opset1">
+		<layer id="1" name="Convert_184686" type="Convert" version="opset1">
 			<data destination_type="i32" />
 			<input>
 				<port id="0" precision="I64">
@@ -25,19 +25,19 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="2" name="Constant_458153" type="Const" version="opset1">
-			<data element_type="u8" shape="558397" offset="0" size="558397" />
+		<layer id="2" name="Constant_184640" type="Const" version="opset1">
+			<data element_type="u8" shape="514030" offset="0" size="514030" />
 			<output>
 				<port id="0" precision="U8">
-					<dim>558397</dim>
+					<dim>514030</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="3" name="StringTensorUnpack_458154" type="StringTensorUnpack" version="extension">
+		<layer id="3" name="StringTensorUnpack_184641" type="StringTensorUnpack" version="extension">
 			<data mode="begins_ends" />
 			<input>
 				<port id="0" precision="U8">
-					<dim>558397</dim>
+					<dim>514030</dim>
 				</port>
 			</input>
 			<output>
@@ -52,7 +52,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="4" name="VocabDecoder_458256" type="VocabDecoder" version="extension">
+		<layer id="4" name="VocabDecoder_184671" type="VocabDecoder" version="extension">
 			<data skip_tokens="0, 1" />
 			<input>
 				<port id="0" precision="I32">
@@ -87,7 +87,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="5" name="CharsToBytes_458257" type="CharsToBytes" version="extension">
+		<layer id="5" name="FuzeRagged_184672" type="FuzeRagged" version="extension">
 			<input>
 				<port id="0" precision="I32">
 					<dim>-1</dim>
@@ -101,39 +101,33 @@
 				<port id="3" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="4" precision="U8">
-					<dim>-1</dim>
-				</port>
 			</input>
 			<output>
-				<port id="5" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="6" precision="I32">
+				<port id="4" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="7" precision="U8">
+				<port id="5" precision="I32">
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="6" name="Constant_458259" type="Const" version="opset1">
-			<data element_type="u8" shape="47" offset="558397" size="47" />
+		<layer id="6" name="Constant_184674" type="Const" version="opset1">
+			<data element_type="u8" shape="47" offset="514030" size="47" />
 			<output>
 				<port id="0" precision="U8">
 					<dim>47</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="7" name="Constant_458261" type="Const" version="opset1">
-			<data element_type="u8" shape="2" offset="558444" size="2" />
+		<layer id="7" name="Constant_184676" type="Const" version="opset1">
+			<data element_type="u8" shape="2" offset="514077" size="2" />
 			<output>
 				<port id="0" precision="U8">
 					<dim>2</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="8" name="RegexNormalization_458262" type="RegexNormalization" version="extension">
+		<layer id="8" name="RegexNormalization_184677" type="RegexNormalization" version="extension">
 			<data global_replace="true" />
 			<input>
 				<port id="0" precision="I32">
@@ -164,7 +158,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="9" name="StringTensorPack_458263" type="StringTensorPack" version="extension">
+		<layer id="9" name="StringTensorPack_184678" type="StringTensorPack" version="extension">
 			<data mode="begins_ends" />
 			<input>
 				<port id="0" precision="I32">
@@ -183,7 +177,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="10" name="Result_458264" type="Result" version="opset1">
+		<layer id="10" name="Result_184679" type="Result" version="opset1">
 			<input>
 				<port id="0" precision="STRING">
 					<dim>-1</dim>
@@ -198,14 +192,13 @@
 		<edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
 		<edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
 		<edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
-		<edge from-layer="4" from-port="8" to-layer="5" to-port="4" />
 		<edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
+		<edge from-layer="4" from-port="8" to-layer="8" to-port="2" />
 		<edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
 		<edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
 		<edge from-layer="4" from-port="4" to-layer="5" to-port="0" />
-		<edge from-layer="5" from-port="5" to-layer="8" to-port="0" />
-		<edge from-layer="5" from-port="6" to-layer="8" to-port="1" />
-		<edge from-layer="5" from-port="7" to-layer="8" to-port="2" />
+		<edge from-layer="5" from-port="4" to-layer="8" to-port="0" />
+		<edge from-layer="5" from-port="5" to-layer="8" to-port="1" />
 		<edge from-layer="6" from-port="0" to-layer="8" to-port="3" />
 		<edge from-layer="7" from-port="0" to-layer="8" to-port="4" />
 		<edge from-layer="8" from-port="5" to-layer="9" to-port="0" />
@@ -214,6 +207,8 @@
 		<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
 	</edges>
 	<rt_info>
+		<bos_token_id value="0" />
 		<eos_token_id value="0" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast'>" />
 	</rt_info>
 </net>

openvino_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5b22fd54f3e41ac3133a9234ee61e654baa23015c88ff27edb3310d0902dd0
-size 1828261828
+oid sha256:250bdb2ad15b87471f34f3d3ad7dae2d1a45b7aa1591337980ccda2303a33d8b
+size 1569419208

openvino_tokenizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c5d770015e1fce984bc6a141f757b4f614587eac66071423500855cce455c1
-size 1166215
+oid sha256:abf9aaae1d4e87049398cc549c6c7cc4d67f79ede0898ea8a5a0e28fd03ca521
+size 1227768

openvino_tokenizer.xml

@@ -1,21 +1,21 @@
 <?xml version="1.0"?>
 <net name="tokenizer" version="11">
 	<layers>
-		<layer id="0" name="Parameter_458065" type="Parameter" version="opset1">
+		<layer id="0" name="Parameter_184558" type="Parameter" version="opset1">
 			<data shape="?" element_type="string" />
 			<output>
-				<port id="0" precision="STRING" names="Parameter_458065">
+				<port id="0" precision="STRING" names="Parameter_184558">
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="1" name="Constant_458072" type="Const" version="opset1">
+		<layer id="1" name="Constant_184564" type="Const" version="opset1">
 			<data element_type="i64" shape="" offset="0" size="8" />
 			<output>
 				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="2" name="StringTensorUnpack_458066" type="StringTensorUnpack" version="extension">
+		<layer id="2" name="StringTensorUnpack_184559" type="StringTensorUnpack" version="extension">
 			<data mode="begins_ends" />
 			<input>
 				<port id="0" precision="STRING">
@@ -34,32 +34,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="3" name="NormalizeUnicode_458067" type="NormalizeUnicode" version="extension">
-			<data normalization_form="NFC" />
-			<input>
-				<port id="0" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="1" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="2" precision="U8">
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="4" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="5" precision="U8">
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="4" name="ShapeOf_458068" type="ShapeOf" version="opset3">
+		<layer id="3" name="ShapeOf_184560" type="ShapeOf" version="opset3">
 			<data output_type="i64" />
 			<input>
 				<port id="0" precision="I32">
@@ -72,19 +47,19 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="5" name="Constant_458069" type="Const" version="opset1">
+		<layer id="4" name="Constant_184561" type="Const" version="opset1">
 			<data element_type="i64" shape="" offset="0" size="8" />
 			<output>
 				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="6" name="Constant_458070" type="Const" version="opset1">
+		<layer id="5" name="Constant_184562" type="Const" version="opset1">
 			<data element_type="i64" shape="" offset="0" size="8" />
 			<output>
 				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="7" name="Gather_458071" type="Gather" version="opset8">
+		<layer id="6" name="Gather_184563" type="Gather" version="opset8">
 			<data batch_dims="0" />
 			<input>
 				<port id="0" precision="I64">
@@ -97,13 +72,13 @@
 				<port id="3" precision="I64" />
 			</output>
 		</layer>
-		<layer id="8" name="Constant_458073" type="Const" version="opset1">
+		<layer id="7" name="Constant_184565" type="Const" version="opset1">
 			<data element_type="i64" shape="" offset="8" size="8" />
 			<output>
 				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="9" name="Range_458074" type="Range" version="opset4">
+		<layer id="8" name="Range_184566" type="Range" version="opset4">
 			<data output_type="i32" />
 			<input>
 				<port id="0" precision="I64" />
@@ -116,19 +91,19 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="10" name="Constant_458076" type="Const" version="opset1">
+		<layer id="9" name="Constant_184567" type="Const" version="opset1">
 			<data element_type="i64" shape="" offset="8" size="8" />
 			<output>
 				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="11" name="Constant_458077" type="Const" version="opset1">
+		<layer id="10" name="Constant_184568" type="Const" version="opset1">
 			<data element_type="i64" shape="" offset="8" size="8" />
 			<output>
 				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="12" name="Add_458078" type="Add" version="opset1">
+		<layer id="11" name="Add_184569" type="Add" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="I64" />
@@ -138,13 +113,13 @@
 				<port id="2" precision="I64" />
 			</output>
 		</layer>
-		<layer id="13" name="Constant_458079" type="Const" version="opset1">
+		<layer id="12" name="Constant_184570" type="Const" version="opset1">
 			<data element_type="i64" shape="" offset="8" size="8" />
 			<output>
 				<port id="0" precision="I64" />
 			</output>
 		</layer>
-		<layer id="14" name="Range_458080" type="Range" version="opset4">
+		<layer id="13" name="Range_184571" type="Range" version="opset4">
 			<data output_type="i32" />
 			<input>
 				<port id="0" precision="I64" />
@@ -157,16 +132,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="15" name="Constant_458143" type="Const" version="opset1">
-			<data element_type="u8" shape="620" offset="16" size="620" />
+		<layer id="14" name="Constant_184633" type="Const" version="opset1">
+			<data element_type="u8" shape="704" offset="16" size="704" />
 			<output>
 				<port id="0" precision="U8">
-					<dim>620</dim>
+					<dim>704</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="16" name="RegexSplit_458144" type="RegexSplit" version="extension">
-			<data behaviour="isolate" invert="false" max_splits="-1" />
+		<layer id="15" name="SpecialTokensSplit_184634" type="SpecialTokensSplit" version="extension">
 			<input>
 				<port id="0" precision="I32">
 					<dim>-1</dim>
@@ -184,7 +158,7 @@
 					<dim>-1</dim>
 				</port>
 				<port id="5" precision="U8">
-					<dim>620</dim>
+					<dim>704</dim>
 				</port>
 			</input>
 			<output>
@@ -203,45 +177,13 @@
 				<port id="10" precision="U8">
 					<dim>-1</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="17" name="Constant_458149" type="Const" version="opset1">
-			<data element_type="u8" shape="64" offset="636" size="64" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>64</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="18" name="Constant_458146" type="Const" version="opset1">
-			<data element_type="u8" shape="399" offset="700" size="399" />
-			<output>
-				<port id="0" precision="U8">
-					<dim>399</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="19" name="StringTensorUnpack_458147" type="StringTensorUnpack" version="extension">
-			<data mode="begins_ends" />
-			<input>
-				<port id="0" precision="U8">
-					<dim>399</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="2" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="3" precision="U8">
+				<port id="11" precision="BOOL">
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="20" name="RegexSplit_458150" type="RegexSplit" version="extension">
-			<data behaviour="isolate" invert="false" max_splits="-1" />
+		<layer id="16" name="NormalizeUnicode_184635" type="NormalizeUnicode" version="extension">
+			<data normalization_form="NFC" />
 			<input>
 				<port id="0" precision="I32">
 					<dim>-1</dim>
@@ -249,47 +191,38 @@
 				<port id="1" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="2" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="4" precision="U8">
-					<dim>-1</dim>
-				</port>
-				<port id="5" precision="U8">
-					<dim>64</dim>
-				</port>
-				<port id="6" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="7" precision="I32">
+				<port id="2" precision="U8">
 					<dim>-1</dim>
 				</port>
-				<port id="8" precision="U8">
+				<port id="3" precision="BOOL">
 					<dim>-1</dim>
 				</port>
 			</input>
 			<output>
-				<port id="9" precision="I32">
+				<port id="4" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="10" precision="I32">
+				<port id="5" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="11" precision="I32">
+				<port id="6" precision="U8">
 					<dim>-1</dim>
 				</port>
-				<port id="12" precision="I32">
+				<port id="7" precision="BOOL">
 					<dim>-1</dim>
 				</port>
-				<port id="13" precision="U8">
-					<dim>-1</dim>
+			</output>
+		</layer>
+		<layer id="17" name="Constant_184637" type="Const" version="opset1">
+			<data element_type="u8" shape="64" offset="720" size="64" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>64</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="21" name="BytesToChars_458151" type="BytesToChars" version="extension">
+		<layer id="18" name="RegexSplit_184638" type="RegexSplit" version="extension">
+			<data behaviour="isolate" invert="false" max_splits="-1" />
 			<input>
 				<port id="0" precision="I32">
 					<dim>-1</dim>
@@ -306,38 +239,47 @@
 				<port id="4" precision="U8">
 					<dim>-1</dim>
 				</port>
+				<port id="5" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="U8">
+					<dim>64</dim>
+				</port>
 			</input>
 			<output>
-				<port id="5" precision="I32">
+				<port id="7" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="6" precision="I32">
+				<port id="8" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="7" precision="I32">
+				<port id="9" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="8" precision="I32">
+				<port id="10" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="9" precision="U8">
+				<port id="11" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="12" precision="BOOL">
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="22" name="Constant_458153" type="Const" version="opset1">
-			<data element_type="u8" shape="558397" offset="1099" size="558397" />
+		<layer id="19" name="Constant_184640" type="Const" version="opset1">
+			<data element_type="u8" shape="514030" offset="784" size="514030" />
 			<output>
 				<port id="0" precision="U8">
-					<dim>558397</dim>
+					<dim>514030</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="23" name="StringTensorUnpack_458154" type="StringTensorUnpack" version="extension">
+		<layer id="20" name="StringTensorUnpack_184641" type="StringTensorUnpack" version="extension">
 			<data mode="begins_ends" />
 			<input>
 				<port id="0" precision="U8">
-					<dim>558397</dim>
+					<dim>514030</dim>
 				</port>
 			</input>
 			<output>
@@ -352,19 +294,19 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="24" name="Constant_458234" type="Const" version="opset1">
-			<data element_type="u8" shape="606619" offset="559496" size="606619" />
+		<layer id="21" name="Constant_184646" type="Const" version="opset1">
+			<data element_type="u8" shape="362936" offset="514814" size="362936" />
 			<output>
 				<port id="0" precision="U8">
-					<dim>606619</dim>
+					<dim>362936</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="25" name="StringTensorUnpack_458235" type="StringTensorUnpack" version="extension">
+		<layer id="22" name="StringTensorUnpack_184647" type="StringTensorUnpack" version="extension">
 			<data mode="begins_ends" />
 			<input>
 				<port id="0" precision="U8">
-					<dim>606619</dim>
+					<dim>362936</dim>
 				</port>
 			</input>
 			<output>
@@ -379,25 +321,19 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="26" name="Constant_458162" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="0" size="8" />
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="27" name="Constant_458156" type="Const" version="opset1">
-			<data element_type="u8" shape="399" offset="700" size="399" />
+		<layer id="23" name="Constant_184649" type="Const" version="opset1">
+			<data element_type="u8" shape="349500" offset="877750" size="349500" />
 			<output>
 				<port id="0" precision="U8">
-					<dim>399</dim>
+					<dim>349500</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="28" name="StringTensorUnpack_458157" type="StringTensorUnpack" version="extension">
+		<layer id="24" name="StringTensorUnpack_184650" type="StringTensorUnpack" version="extension">
 			<data mode="begins_ends" />
 			<input>
 				<port id="0" precision="U8">
-					<dim>399</dim>
+					<dim>349500</dim>
 				</port>
 			</input>
 			<output>
@@ -412,150 +348,43 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="29" name="ShapeOf_458158" type="ShapeOf" version="opset3">
-			<data output_type="i64" />
-			<input>
-				<port id="0" precision="I32">
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="1" precision="I64">
-					<dim>1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="30" name="Constant_458159" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="0" size="8" />
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="31" name="Constant_458160" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="0" size="8" />
+		<layer id="25" name="Constant_184643" type="Const" version="opset1">
+			<data element_type="u8" shape="414" offset="1227250" size="414" />
 			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="32" name="Gather_458161" type="Gather" version="opset8">
-			<data batch_dims="0" />
-			<input>
-				<port id="0" precision="I64">
-					<dim>1</dim>
+				<port id="0" precision="U8">
+					<dim>414</dim>
 				</port>
-				<port id="1" precision="I64" />
-				<port id="2" precision="I64" />
-			</input>
-			<output>
-				<port id="3" precision="I64" />
 			</output>
 		</layer>
-		<layer id="33" name="Constant_458163" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="8" size="8" />
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="34" name="Range_458164" type="Range" version="opset4">
-			<data output_type="i32" />
+		<layer id="26" name="StringTensorUnpack_184644" type="StringTensorUnpack" version="extension">
+			<data mode="begins_ends" />
 			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64" />
-				<port id="2" precision="I64" />
-			</input>
-			<output>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
+				<port id="0" precision="U8">
+					<dim>414</dim>
 				</port>
-			</output>
-		</layer>
-		<layer id="35" name="Constant_458166" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="8" size="8" />
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="36" name="Constant_458167" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="8" size="8" />
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="37" name="Add_458168" type="Add" version="opset1">
-			<data auto_broadcast="numpy" />
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64" />
 			</input>
 			<output>
-				<port id="2" precision="I64" />
-			</output>
-		</layer>
-		<layer id="38" name="Constant_458169" type="Const" version="opset1">
-			<data element_type="i64" shape="" offset="8" size="8" />
-			<output>
-				<port id="0" precision="I64" />
-			</output>
-		</layer>
-		<layer id="39" name="Range_458170" type="Range" version="opset4">
-			<data output_type="i32" />
-			<input>
-				<port id="0" precision="I64" />
-				<port id="1" precision="I64" />
-				<port id="2" precision="I64" />
-			</input>
-			<output>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
-				</port>
-			</output>
-		</layer>
-		<layer id="40" name="BytesToChars_458232" type="BytesToChars" version="extension">
-			<input>
-				<port id="0" precision="I32">
-					<dim>-1</dim>
-				</port>
 				<port id="1" precision="I32">
 					<dim>-1</dim>
 				</port>
 				<port id="2" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="3" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="4" precision="U8">
-					<dim>-1</dim>
-				</port>
-			</input>
-			<output>
-				<port id="5" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="6" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="7" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="8" precision="I32">
-					<dim>-1</dim>
-				</port>
-				<port id="9" precision="U8">
+				<port id="3" precision="U8">
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="41" name="Constant_458236" type="Const" version="opset1">
-			<data element_type="i32" shape="23" offset="1166115" size="92" />
+		<layer id="27" name="Constant_184651" type="Const" version="opset1">
+			<data element_type="i32" shape="24" offset="1227664" size="96" />
 			<output>
 				<port id="0" precision="I32">
-					<dim>23</dim>
+					<dim>24</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="42" name="BPETokenizer_458237" type="BPETokenizer" version="extension">
-			<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" />
+		<layer id="28" name="BPETokenizer_184652" type="BPETokenizer" version="extension">
+			<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="20000" />
 			<input>
 				<port id="0" precision="I32">
 					<dim>-1</dim>
@@ -600,22 +429,31 @@
 					<dim>-1</dim>
 				</port>
 				<port id="14" precision="I32">
-					<dim>23</dim>
+					<dim>-1</dim>
 				</port>
-			</input>
-			<output>
 				<port id="15" precision="I32">
 					<dim>-1</dim>
 				</port>
-				<port id="16" precision="I32">
+				<port id="16" precision="U8">
 					<dim>-1</dim>
 				</port>
 				<port id="17" precision="I32">
+					<dim>24</dim>
+				</port>
+			</input>
+			<output>
+				<port id="18" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="19" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="20" precision="I32">
 					<dim>-1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="43" name="Subtract_458238" type="Subtract" version="opset1">
+		<layer id="29" name="Subtract_184653" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="I32">
@@ -631,13 +469,13 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="44" name="Constant_458239" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="1166207" size="4" />
+		<layer id="30" name="Constant_184654" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="1227760" size="4" />
 			<output>
 				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="45" name="Minimum_458240" type="Minimum" version="opset1">
+		<layer id="31" name="Minimum_184655" type="Minimum" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="I32">
@@ -651,7 +489,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="46" name="Add_458241" type="Add" version="opset1">
+		<layer id="32" name="Subtract_184656" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="I32">
@@ -667,15 +505,15 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="47" name="Constant_458242" type="Const" version="opset1">
-			<data element_type="i32" shape="1" offset="1166211" size="4" />
+		<layer id="33" name="Constant_184657" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="1227764" size="4" />
 			<output>
 				<port id="0" precision="I32">
 					<dim>1</dim>
 				</port>
 			</output>
 		</layer>
-		<layer id="48" name="CombineSegments_458243" type="CombineSegments" version="extension">
+		<layer id="34" name="CombineSegments_184658" type="CombineSegments" version="extension">
 			<input>
 				<port id="0" precision="I32">
 					<dim>-1</dim>
@@ -711,7 +549,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="49" name="Subtract_458244" type="Subtract" version="opset1">
+		<layer id="35" name="Subtract_184659" type="Subtract" version="opset1">
 			<data auto_broadcast="numpy" />
 			<input>
 				<port id="0" precision="I32">
@@ -727,13 +565,13 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="50" name="Constant_458245" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="1166211" size="4" />
+		<layer id="36" name="Constant_184660" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="1227764" size="4" />
 			<output>
 				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="51" name="ReduceMax_458246" type="ReduceMax" version="opset1">
+		<layer id="37" name="ReduceMax_184661" type="ReduceMax" version="opset1">
 			<data keep_dims="false" />
 			<input>
 				<port id="0" precision="I32">
@@ -745,14 +583,14 @@
 				<port id="2" precision="I32" />
 			</output>
 		</layer>
-		<layer id="52" name="Constant_458247" type="Const" version="opset1">
-			<data element_type="i32" shape="" offset="1166211" size="4" />
+		<layer id="38" name="Constant_184662" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="1227764" size="4" />
 			<output>
 				<port id="0" precision="I32" />
 			</output>
 		</layer>
-		<layer id="53" name="RaggedToDense_458248" type="RaggedToDense" version="extension">
-			<data pad_right="true" />
+		<layer id="39" name="RaggedToDense_184663" type="RaggedToDense" version="extension">
+			<data pad_right="false" />
 			<input>
 				<port id="0" precision="I32">
 					<dim>-1</dim>
@@ -777,7 +615,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="54" name="Convert_458249" type="Convert" version="opset1">
+		<layer id="40" name="Convert_184664" type="Convert" version="opset1">
 			<data destination_type="i32" />
 			<input>
 				<port id="0" precision="BOOL">
@@ -792,7 +630,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="55" name="Convert_458249" type="Convert" version="opset1">
+		<layer id="41" name="Convert_184664" type="Convert" version="opset1">
 			<data destination_type="i64" />
 			<input>
 				<port id="0" precision="I32">
@@ -807,7 +645,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="57" name="RaggedToDense_458248.0" type="Convert" version="opset1">
+		<layer id="43" name="RaggedToDense_184663.0" type="Convert" version="opset1">
 			<data destination_type="i64" />
 			<input>
 				<port id="0" precision="I32">
@@ -822,7 +660,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="58" name="Result_458252" type="Result" version="opset1">
+		<layer id="44" name="Result_184667" type="Result" version="opset1">
 			<input>
 				<port id="0" precision="I64">
 					<dim>-1</dim>
@@ -830,7 +668,7 @@
 				</port>
 			</input>
 		</layer>
-		<layer id="56" name="Result_458254" type="Result" version="opset1">
+		<layer id="42" name="Result_184669" type="Result" version="opset1">
 			<input>
 				<port id="0" precision="I64">
 					<dim>-1</dim>
@@ -841,103 +679,85 @@
 	</layers>
 	<edges>
 		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
-		<edge from-layer="1" from-port="0" to-layer="9" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
 		<edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
-		<edge from-layer="2" from-port="2" to-layer="3" to-port="1" />
-		<edge from-layer="2" from-port="3" to-layer="3" to-port="2" />
-		<edge from-layer="3" from-port="5" to-layer="16" to-port="4" />
-		<edge from-layer="3" from-port="4" to-layer="16" to-port="3" />
-		<edge from-layer="3" from-port="3" to-layer="16" to-port="2" />
-		<edge from-layer="3" from-port="3" to-layer="4" to-port="0" />
-		<edge from-layer="4" from-port="1" to-layer="7" to-port="0" />
-		<edge from-layer="5" from-port="0" to-layer="7" to-port="1" />
-		<edge from-layer="6" from-port="0" to-layer="7" to-port="2" />
-		<edge from-layer="7" from-port="3" to-layer="9" to-port="1" />
-		<edge from-layer="7" from-port="3" to-layer="12" to-port="0" />
-		<edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
-		<edge from-layer="9" from-port="3" to-layer="16" to-port="0" />
-		<edge from-layer="10" from-port="0" to-layer="14" to-port="0" />
-		<edge from-layer="11" from-port="0" to-layer="12" to-port="1" />
-		<edge from-layer="12" from-port="2" to-layer="14" to-port="1" />
-		<edge from-layer="13" from-port="0" to-layer="14" to-port="2" />
-		<edge from-layer="14" from-port="3" to-layer="16" to-port="1" />
-		<edge from-layer="15" from-port="0" to-layer="16" to-port="5" />
-		<edge from-layer="16" from-port="6" to-layer="20" to-port="0" />
-		<edge from-layer="16" from-port="7" to-layer="20" to-port="1" />
-		<edge from-layer="16" from-port="8" to-layer="20" to-port="2" />
-		<edge from-layer="16" from-port="9" to-layer="20" to-port="3" />
-		<edge from-layer="16" from-port="10" to-layer="20" to-port="4" />
-		<edge from-layer="17" from-port="0" to-layer="20" to-port="5" />
-		<edge from-layer="18" from-port="0" to-layer="19" to-port="0" />
-		<edge from-layer="19" from-port="1" to-layer="20" to-port="6" />
-		<edge from-layer="19" from-port="2" to-layer="20" to-port="7" />
-		<edge from-layer="19" from-port="3" to-layer="20" to-port="8" />
-		<edge from-layer="20" from-port="9" to-layer="21" to-port="0" />
-		<edge from-layer="20" from-port="13" to-layer="21" to-port="4" />
-		<edge from-layer="20" from-port="12" to-layer="21" to-port="3" />
-		<edge from-layer="20" from-port="10" to-layer="21" to-port="1" />
-		<edge from-layer="20" from-port="11" to-layer="21" to-port="2" />
-		<edge from-layer="21" from-port="9" to-layer="42" to-port="4" />
-		<edge from-layer="21" from-port="8" to-layer="42" to-port="3" />
-		<edge from-layer="21" from-port="7" to-layer="42" to-port="2" />
-		<edge from-layer="21" from-port="6" to-layer="42" to-port="1" />
-		<edge from-layer="21" from-port="5" to-layer="42" to-port="0" />
-		<edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
-		<edge from-layer="23" from-port="3" to-layer="42" to-port="7" />
-		<edge from-layer="23" from-port="2" to-layer="42" to-port="6" />
-		<edge from-layer="23" from-port="1" to-layer="42" to-port="5" />
-		<edge from-layer="24" from-port="0" to-layer="25" to-port="0" />
-		<edge from-layer="25" from-port="3" to-layer="42" to-port="10" />
-		<edge from-layer="25" from-port="2" to-layer="42" to-port="9" />
-		<edge from-layer="25" from-port="1" to-layer="42" to-port="8" />
-		<edge from-layer="26" from-port="0" to-layer="34" to-port="0" />
-		<edge from-layer="27" from-port="0" to-layer="28" to-port="0" />
-		<edge from-layer="28" from-port="2" to-layer="40" to-port="3" />
-		<edge from-layer="28" from-port="1" to-layer="29" to-port="0" />
-		<edge from-layer="28" from-port="3" to-layer="40" to-port="4" />
-		<edge from-layer="28" from-port="1" to-layer="40" to-port="2" />
-		<edge from-layer="29" from-port="1" to-layer="32" to-port="0" />
-		<edge from-layer="30" from-port="0" to-layer="32" to-port="1" />
-		<edge from-layer="31" from-port="0" to-layer="32" to-port="2" />
-		<edge from-layer="32" from-port="3" to-layer="34" to-port="1" />
-		<edge from-layer="32" from-port="3" to-layer="37" to-port="0" />
-		<edge from-layer="33" from-port="0" to-layer="34" to-port="2" />
-		<edge from-layer="34" from-port="3" to-layer="40" to-port="0" />
-		<edge from-layer="35" from-port="0" to-layer="39" to-port="0" />
+		<edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
+		<edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
+		<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
+		<edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
+		<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
+		<edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
+		<edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
+		<edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
+		<edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
+		<edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
+		<edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
+		<edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
+		<edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
+		<edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
+		<edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
+		<edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
+		<edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
+		<edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
+		<edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
+		<edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
+		<edge from-layer="18" from-port="11" to-layer="28" to-port="4" />
+		<edge from-layer="18" from-port="10" to-layer="28" to-port="3" />
+		<edge from-layer="18" from-port="9" to-layer="28" to-port="2" />
+		<edge from-layer="18" from-port="8" to-layer="28" to-port="1" />
+		<edge from-layer="18" from-port="7" to-layer="28" to-port="0" />
+		<edge from-layer="19" from-port="0" to-layer="20" to-port="0" />
+		<edge from-layer="20" from-port="1" to-layer="28" to-port="5" />
+		<edge from-layer="20" from-port="2" to-layer="28" to-port="6" />
+		<edge from-layer="20" from-port="3" to-layer="28" to-port="7" />
+		<edge from-layer="21" from-port="0" to-layer="22" to-port="0" />
+		<edge from-layer="22" from-port="1" to-layer="28" to-port="8" />
+		<edge from-layer="22" from-port="2" to-layer="28" to-port="9" />
+		<edge from-layer="22" from-port="3" to-layer="28" to-port="10" />
+		<edge from-layer="23" from-port="0" to-layer="24" to-port="0" />
+		<edge from-layer="24" from-port="1" to-layer="28" to-port="11" />
+		<edge from-layer="24" from-port="2" to-layer="28" to-port="12" />
+		<edge from-layer="24" from-port="3" to-layer="28" to-port="13" />
+		<edge from-layer="25" from-port="0" to-layer="26" to-port="0" />
+		<edge from-layer="26" from-port="1" to-layer="28" to-port="14" />
+		<edge from-layer="26" from-port="2" to-layer="28" to-port="15" />
+		<edge from-layer="26" from-port="3" to-layer="28" to-port="16" />
+		<edge from-layer="27" from-port="0" to-layer="28" to-port="17" />
+		<edge from-layer="28" from-port="19" to-layer="29" to-port="0" />
+		<edge from-layer="28" from-port="18" to-layer="29" to-port="1" />
+		<edge from-layer="28" from-port="19" to-layer="32" to-port="0" />
+		<edge from-layer="28" from-port="20" to-layer="34" to-port="2" />
+		<edge from-layer="28" from-port="19" to-layer="34" to-port="1" />
+		<edge from-layer="29" from-port="2" to-layer="31" to-port="0" />
+		<edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
+		<edge from-layer="31" from-port="2" to-layer="32" to-port="1" />
+		<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
+		<edge from-layer="33" from-port="0" to-layer="34" to-port="3" />
+		<edge from-layer="34" from-port="5" to-layer="39" to-port="1" />
+		<edge from-layer="34" from-port="6" to-layer="39" to-port="2" />
+		<edge from-layer="34" from-port="4" to-layer="39" to-port="0" />
+		<edge from-layer="34" from-port="4" to-layer="35" to-port="1" />
+		<edge from-layer="34" from-port="5" to-layer="35" to-port="0" />
+		<edge from-layer="35" from-port="2" to-layer="37" to-port="0" />
 		<edge from-layer="36" from-port="0" to-layer="37" to-port="1" />
-		<edge from-layer="37" from-port="2" to-layer="39" to-port="1" />
-		<edge from-layer="38" from-port="0" to-layer="39" to-port="2" />
-		<edge from-layer="39" from-port="3" to-layer="40" to-port="1" />
-		<edge from-layer="40" from-port="7" to-layer="42" to-port="11" />
-		<edge from-layer="40" from-port="8" to-layer="42" to-port="12" />
-		<edge from-layer="40" from-port="9" to-layer="42" to-port="13" />
-		<edge from-layer="41" from-port="0" to-layer="42" to-port="14" />
-		<edge from-layer="42" from-port="17" to-layer="48" to-port="2" />
-		<edge from-layer="42" from-port="15" to-layer="48" to-port="0" />
-		<edge from-layer="42" from-port="15" to-layer="46" to-port="0" />
-		<edge from-layer="42" from-port="15" to-layer="43" to-port="1" />
-		<edge from-layer="42" from-port="16" to-layer="43" to-port="0" />
-		<edge from-layer="43" from-port="2" to-layer="45" to-port="0" />
-		<edge from-layer="44" from-port="0" to-layer="45" to-port="1" />
-		<edge from-layer="45" from-port="2" to-layer="46" to-port="1" />
-		<edge from-layer="46" from-port="2" to-layer="48" to-port="1" />
-		<edge from-layer="47" from-port="0" to-layer="48" to-port="3" />
-		<edge from-layer="48" from-port="5" to-layer="49" to-port="0" />
-		<edge from-layer="48" from-port="4" to-layer="49" to-port="1" />
-		<edge from-layer="48" from-port="4" to-layer="53" to-port="0" />
-		<edge from-layer="48" from-port="5" to-layer="53" to-port="1" />
-		<edge from-layer="48" from-port="6" to-layer="53" to-port="2" />
-		<edge from-layer="49" from-port="2" to-layer="51" to-port="0" />
-		<edge from-layer="50" from-port="0" to-layer="51" to-port="1" />
-		<edge from-layer="51" from-port="2" to-layer="53" to-port="3" />
-		<edge from-layer="52" from-port="0" to-layer="53" to-port="4" />
-		<edge from-layer="53" from-port="6" to-layer="54" to-port="0" />
-		<edge from-layer="53" from-port="5" to-layer="57" to-port="0" />
-		<edge from-layer="54" from-port="1" to-layer="55" to-port="0" />
-		<edge from-layer="55" from-port="1" to-layer="56" to-port="0" />
-		<edge from-layer="57" from-port="1" to-layer="58" to-port="0" />
+		<edge from-layer="37" from-port="2" to-layer="39" to-port="3" />
+		<edge from-layer="38" from-port="0" to-layer="39" to-port="4" />
+		<edge from-layer="39" from-port="6" to-layer="40" to-port="0" />
+		<edge from-layer="39" from-port="5" to-layer="43" to-port="0" />
+		<edge from-layer="40" from-port="1" to-layer="41" to-port="0" />
+		<edge from-layer="41" from-port="1" to-layer="42" to-port="0" />
+		<edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
 	</edges>
 	<rt_info>
+		<bos_token_id value="0" />
 		<eos_token_id value="0" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.gpt_neox.tokenization_gpt_neox_fast.GPTNeoXTokenizerFast'>" />
 	</rt_info>
 </net>