Upload folder using huggingface_hub

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,146 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model:
+- mistral-community/pixtral-12b
+base_model_relation: quantized
+---
+
+# pixtral-12b-int4-ov
+
+ * Model creator: [mistral-community](https://huggingface.co/mistral-community)
+ * Original model: [mistral-community/pixtral-12b](https://huggingface.co/mistral-community/pixtral-12b)
+
+## Description
+
+This is [mistral-community/pixtral-12b](https://huggingface.co/mistral-community/pixtral-12b) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2025/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT4 by [NNCF](https://github.com/openvinotoolkit/nncf).
+
+
+## Quantization Parameters
+
+Weight compression was performed using `nncf.compress_weights` with the following parameters:
+
+* mode: **INT4_ASYM**
+
+## Compatibility
+
+The provided OpenVINO™ IR model is compatible with:
+
+* OpenVINO version 2025.2.0 and higher
+* Optimum Intel 1.26.0 and higher
+
+## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
+
+1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
+
+```
+pip install --pre -U --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release openvino_tokenizers openvino
+
+pip install git+https://github.com/huggingface/optimum-intel.git
+```
+
+2. Run model inference
+
+```
+from PIL import Image 
+import requests 
+from optimum.intel.openvino import OVModelForVisualCausalLM
+from transformers import AutoTokenizer, TextStreamer
+
+model_id = "OpenVINO/pixtral-12b-int4-ov"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+
+ov_model = OVModelForVisualCausalLM.from_pretrained(model_id, trust_remote_code=True)
+prompt = "What is unusual on this picture?"
+
+url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
+image = Image.open(requests.get(url, stream=True).raw)
+
+inputs = ov_model.preprocess_inputs(text=prompt, image=image, tokenizer=tokenizer, config=ov_model.config)
+
+generation_args = { 
+    "max_new_tokens": 100, 
+    "streamer": TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+} 
+
+generate_ids = ov_model.generate(**inputs, **generation_args)
+
+generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
+response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True)[0]
+
+```
+
+## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
+
+1. Install packages required for using OpenVINO GenAI.
+```
+pip install --pre -U --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release openvino openvino-tokenizers openvino-genai
+
+pip install huggingface_hub
+```
+
+2. Download model from HuggingFace Hub
+   
+```
+import huggingface_hub as hf_hub
+
+model_id = "OpenVINO/pixtral-12b-int4-ov"
+model_path = "pixtral-12b-int4-ov"
+
+hf_hub.snapshot_download(model_id, local_dir=model_path)
+
+```
+
+1. Run model inference:
+
+```
+import openvino_genai as ov_genai
+import requests
+from PIL import Image
+from io import BytesIO
+import numpy as np
+import openvino as ov
+
+device = "CPU"
+pipe = ov_genai.VLMPipeline(model_path, device)
+
+def load_image(image_file):
+    if isinstance(image_file, str) and (image_file.startswith("http") or image_file.startswith("https")):
+        response = requests.get(image_file)
+        image = Image.open(BytesIO(response.content)).convert("RGB")
+    else:
+        image = Image.open(image_file).convert("RGB")
+    image_data = np.array(image.getdata()).reshape(1, image.size[1], image.size[0], 3).astype(np.byte)
+    return ov.Tensor(image_data)
+
+prompt = "What is unusual on this picture?"
+
+url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
+image_tensor = load_image(url)
+
+def streamer(subword: str) -> bool:
+    print(subword, end="", flush=True)
+    return False
+
+pipe.start_chat()
+output = pipe.generate(prompt, image=image_tensor, max_new_tokens=100, streamer=streamer)
+pipe.finish_chat()
+```
+
+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](https://huggingface.co/mistral-community/pixtral-12b) for limitations.
+
+## Legal information
+
+The original model is distributed under [apache-2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) license. More details can be found in [original model card](https://huggingface.co/mistral-community/pixtral-12b).
+
+## Disclaimer
+
+Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.
+

chat_template.jinja

@@ -0,0 +1,4 @@
+{%- if messages[0]["role"] == "system" %}{%- set system_message = messages[0]["content"] %}{%- set loop_messages = messages[1:] %}
+{%- else %}{%- set loop_messages = messages %}{%- endif %}{{- bos_token }}{%- for message in loop_messages %}{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif %}{%- if message["role"] == "user" %}{%- if loop.last and system_message is defined %}{{- "[INST]" + system_message + "
+
+" }}{%- else %}{{ "[INST]" }}{%- endif %}{%- endif %}{%- if message["content"] is not string %}{%- for chunk in message["content"] %}{%- if chunk["type"] == "text" %}{%- if "content" in chunk %}{{- chunk["content"] }}{%- elif "text" in chunk %}{{- chunk["text"] }}{%- endif %}{%- elif chunk["type"] == "image" %}{{- "[IMG]" }}{%- else %}{{- raise_exception("Unrecognized content type!") }}{%- endif %}{%- endfor %}{%- else %}{{- message["content"] }}{%- endif %}{%- if message["role"] == "user" %}{{- "[/INST]" }}{%- elif message["role"] == "assistant" %}{{- eos_token}}{%- else %}{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}{%- endif %}{%- endfor %}

config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 1,
+  "image_token_index": 10,
+  "model_type": "llava",
+  "multimodal_projector_bias": true,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_composition": true,
+    "max_position_embeddings": 1024000,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_composition": true,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 16,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "full"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.53.3"
+}

openvino_config.json

@@ -0,0 +1,29 @@
+{
+  "dtype": "int4",
+  "input_info": null,
+  "optimum_version": "1.27.0",
+  "output_attentions": false,
+  "quantization_config": {
+    "all_layers": null,
+    "backup_precision": null,
+    "bits": 4,
+    "dataset": null,
+    "dtype": "int4",
+    "gptq": null,
+    "group_size": 128,
+    "ignored_scope": null,
+    "lora_correction": null,
+    "num_samples": null,
+    "processor": null,
+    "quant_method": "default",
+    "ratio": 1.0,
+    "scale_estimation": null,
+    "sensitivity_metric": null,
+    "statistics_path": null,
+    "sym": false,
+    "tokenizer": null,
+    "trust_remote_code": false
+  },
+  "save_onnx_model": false,
+  "transformers_version": "4.53.3"
+}

openvino_language_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec64c98cf3020db1871a81712386d8e0d68986904e0a81bc8a698e165b90cde
+size 6338728549

openvino_text_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17717e2eb187715be5e9c01b85cbef5185d7c2fe0874fd95b006f45bbfb9d640
+size 671350788

openvino_text_embeddings_model.xml

@@ -0,0 +1,179 @@
+<?xml version="1.0"?>
+<net name="Model3" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="131072, 5120" offset="0" size="671088640" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_1417199" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="131072, 1" offset="671088640" size="262144" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>131072</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>131072</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="ov_ext::embedding/Convert_1" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="ov_ext::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="671350784" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="8" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>131072</dim>
+					<dim>5120</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32" names="inputs_embeds">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>5120</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Result_39958" type="Result" version="opset1" output_names="inputs_embeds">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>5120</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="8" to-port="0" />
+		<edge from-layer="6" from-port="1" 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="9" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<version value="2.17.0" />
+			<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': {}}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<compression_format value="dequantize" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.17.0" />
+			<optimum_intel_version value="1.26.0.dev0+e9c57b9" />
+			<optimum_version value="1.27.0" />
+			<pytorch_version value="2.8.0+cpu" />
+			<transformers_version value="4.53.3" />
+		</optimum>
+	</rt_info>
+</net>

openvino_vision_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99689065da64cb43f89171e1f249971c6a9d3cde52507822a22314bf15a8274
+size 436050236

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "processor_class": "PixtralProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

processor_config.json

@@ -0,0 +1,8 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_token": "[IMG]",
+  "patch_size": 16,
+  "processor_class": "PixtralProcessor",
+  "spatial_merge_size": 1
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcdf3e6b96371b9a5c8673bdf2f1bc838b994b73a6fa995dca62196346aaddb5
+size 17077311