add mixed quantized model

openvino_config.json

@@ -1,72 +1,3 @@
-{
-  "dtype": "int8_int8_int8",
-  "input_info": null,
-  "optimum_version": "1.26.1",
-  "quantization_config": {
-    "dataset": "contextual",
-    "ignored_scope": null,
-    "num_samples": 200,
-    "processor": null,
-    "quantization_configs": {
-      "lm_model": {
-        "bits": 8,
-        "dataset": null,
-        "dtype": "int8",
-        "fast_bias_correction": true,
-        "ignored_scope": null,
-        "model_type": "transformer",
-        "num_samples": null,
-        "overflow_fix": "disable",
-        "processor": null,
-        "smooth_quant_alpha": null,
-        "sym": false,
-        "tokenizer": null,
-        "trust_remote_code": false
-      },
-      "text_embeddings_model": {
-        "all_layers": null,
-        "backup_precision": null,
-        "bits": 8,
-        "dataset": null,
-        "dtype": "int8",
-        "gptq": null,
-        "group_size": -1,
-        "ignored_scope": null,
-        "lora_correction": null,
-        "num_samples": null,
-        "processor": null,
-        "quant_method": "default",
-        "ratio": 1.0,
-        "scale_estimation": null,
-        "sensitivity_metric": null,
-        "sym": false,
-        "tokenizer": null,
-        "trust_remote_code": false
-      },
-      "vision_embeddings_model": {
-        "all_layers": null,
-        "backup_precision": null,
-        "bits": 8,
-        "dataset": null,
-        "dtype": "int8",
-        "gptq": null,
-        "group_size": -1,
-        "ignored_scope": null,
-        "lora_correction": null,
-        "num_samples": null,
-        "processor": null,
-        "quant_method": "default",
-        "ratio": 1.0,
-        "scale_estimation": null,
-        "sensitivity_metric": null,
-        "sym": false,
-        "tokenizer": null,
-        "trust_remote_code": false
-      }
-    },
-    "tokenizer": null,
-    "trust_remote_code": false
-  },
-  "save_onnx_model": false,
-  "transformers_version": "4.52.4"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad74dd7a61f3d7f164762b506879ac89894aba6dcdb3ff28bab1a6a3e0740da
+size 2022

openvino_language_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c144f9eb51ff2a1546d12b0a4b96b4deb544e05ebede49a7f6c45e43f69c60
-size 135909156
+oid sha256:88460ca0040d4138a0dc22ccb757fe8628ac3fcf6a0721834c3648eaeafa7ce3
+size 135308933

openvino_text_embeddings_model.xml

@@ -1,5 +1,5 @@
 <?xml version="1.0"?>
-<net name="Model54" version="11">
+<net name="Model3" version="11">
 	<layers>
 		<layer id="0" name="input" type="Parameter" version="opset1">
 			<data shape="?,?" element_type="i64" />
@@ -19,7 +19,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="2" name="Convert_185024" type="Convert" version="opset1">
+		<layer id="2" name="Convert_891888" type="Convert" version="opset1">
 			<data destination_type="f16" />
 			<input>
 				<port id="0" precision="U8">
@@ -43,7 +43,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="4" name="Convert_185027" type="Convert" version="opset1">
+		<layer id="4" name="Convert_891891" type="Convert" version="opset1">
 			<data destination_type="f16" />
 			<input>
 				<port id="0" precision="U8">
@@ -162,7 +162,7 @@
 				</port>
 			</output>
 		</layer>
-		<layer id="12" name="Result_189847" type="Result" version="opset1" output_names="inputs_embeds">
+		<layer id="12" name="Result_10181" type="Result" version="opset1" output_names="inputs_embeds">
 			<input>
 				<port id="0" precision="FP32">
 					<dim>-1</dim>
@@ -187,16 +187,16 @@
 		<edge from-layer="11" from-port="3" to-layer="12" to-port="0" />
 	</edges>
 	<rt_info>
-		<Runtime_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" />
+		<Runtime_version value="2025.3.0-19807-44526285f24-releases/2025/3" />
 		<conversion_parameters>
 			<framework value="pytorch" />
 			<is_python_object value="True" />
 		</conversion_parameters>
 		<nncf>
 			<friendly_names_were_updated value="True" />
-			<version value="2.17.0" />
+			<version value="2.18.0" />
 			<weight_compression>
-				<advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'lora_adapter_rank': 256, 'backend_params': {}}" />
+				<advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'ignore', 'min_adjusted_group_size': 16, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
 				<all_layers value="False" />
 				<awq value="False" />
 				<backup_mode value="int8_asym" />
@@ -212,11 +212,11 @@
 			</weight_compression>
 		</nncf>
 		<optimum>
-			<nncf_version value="2.17.0" />
-			<optimum_intel_version value="1.25.0.dev0+06c0a597" />
-			<optimum_version value="1.26.1" />
-			<pytorch_version value="2.7.1+cpu" />
-			<transformers_version value="4.52.4" />
+			<nncf_version value="2.18.0" />
+			<optimum_intel_version value="1.26.0.dev0+f9cff03" />
+			<optimum_version value="2.0.0.dev0" />
+			<pytorch_version value="2.8.0" />
+			<transformers_version value="4.55.4" />
 		</optimum>
 	</rt_info>
 </net>

openvino_vision_embeddings_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109f9b085ef81295816a6687636a21147cb2aafafb345846da7ad2c29cc73b7c
-size 94133488
+oid sha256:57e5aca259ca410ab26f6563bb00793c2d58b80eb58a3227c1faa7dd79ccddfa
+size 94526592