Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+license_link: https://choosealicense.com/licenses/apache-2.0/
+---
+# open_llama_3b_v2-int4-ov
+* Model creator: [Openlm-research](https://huggingface.co/openlm-research)
+ * Original model: [open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2)
+
+## Description
+This is [open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/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_sym**
+* ratio: **1.0**
+* group_size: **64**
+* all_layers: **True**
+
+For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).
+
+
+## Compatibility
+
+The provided OpenVINO™ IR model is compatible with:
+
+* OpenVINO version 2024.1.0 and higher
+* Optimum Intel 1.16.0 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:
+
+```
+pip install optimum[openvino]
+```
+
+2. Run model inference:
+
+```
+from transformers import AutoTokenizer
+from optimum.intel.openvino import OVModelForCausalLM
+
+model_id = "OpenVINO/open_llama_3b_v2-int4-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForCausalLM.from_pretrained(model_id)
+
+inputs = tokenizer("What is OpenVINO?", return_tensors="pt")
+
+outputs = model.generate(**inputs, max_length=200)
+text = tokenizer.batch_decode(outputs)[0]
+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).
+
+## Limitations
+
+Check the original model card for [original model card](https://huggingface.co/openlm-research/open_llama_3b_v2) for limitations.
+
+## Legal information
+
+The original model is distributed under [apache-2.0](https://choosealicense.com/licenses/apache-2.0/) license. More details can be found in [original model card](https://huggingface.co/openlm-research/open_llama_3b_v2).
+
+## 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.

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "openlm-research/open_llama_3b_v2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

openvino_detokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9200b58939b5f15eda267b46cd367416c6ffec891653b50930b2cb0944c0f112
+size 511574

openvino_detokenizer.xml

@@ -0,0 +1,97 @@
+<?xml version="1.0"?>
+<net name="detokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_143668" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="Parameter_143668">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_143648" type="Const" version="opset1">
+			<data element_type="u8" shape="511574" offset="0" size="511574" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>511574</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_143678" 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="3" name="SentencepieceDetokenizer_143669" type="SentencepieceDetokenizer" version="extension">
+			<input>
+				<port id="0" precision="U8">
+					<dim>511574</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<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>
+			</output>
+		</layer>
+		<layer id="4" name="StringTensorPack_143670" type="StringTensorPack" version="extension">
+			<data mode="begins_ends" />
+			<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="STRING" names="string_output">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Result_143671" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="3" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
+		<edge from-layer="3" from-port="2" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="3" to-layer="4" to-port="1" />
+		<edge from-layer="3" from-port="4" to-layer="4" to-port="2" />
+		<edge from-layer="4" from-port="3" to-layer="5" to-port="0" />
+	</edges>
+	<rt_info>
+		<eos_token_id value="2" />
+	</rt_info>
+</net>

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392979a68e8467eade2841358a65ad574d4718c62b13fe944cb3e58b5854a662
+size 1820902984

openvino_tokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b77cf2b305f5fcd17706d2242cec5e69576e6888853fee55fef0c734926605
+size 511582

openvino_tokenizer.xml

@@ -0,0 +1,231 @@
+<?xml version="1.0"?>
+<net name="tokenizer" version="11">
+	<layers>
+		<layer id="0" name="string_input" type="Parameter" version="opset1">
+			<data shape="?" element_type="string" />
+			<output>
+				<port id="0" precision="STRING" names="string_input">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_143654" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="2" name="Constant_143647" type="Const" version="opset1">
+			<data element_type="u8" shape="511574" offset="4" size="511574" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>511574</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="SentencepieceTokenizer_143650" type="SentencepieceTokenizer" version="extension">
+			<data nbest_size="0" alpha="0" add_bos="true" add_eos="false" reverse="false" />
+			<input>
+				<port id="0" precision="U8">
+					<dim>511574</dim>
+				</port>
+				<port id="1" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64">
+					<dim>-1</dim>
+					<dim>2</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Broadcast_143655" type="Broadcast" version="opset3">
+			<data mode="numpy" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Constant_143656" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="511578" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="6" name="ShapeOf_143657" 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="7" name="Broadcast_143658" type="Broadcast" version="opset3">
+			<data mode="numpy" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="ScatterNDUpdate_143662" type="ScatterNDUpdate" version="opset4">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>-1</dim>
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="ScatterNDUpdate_143662" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="attention_mask">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="Constant_143651" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="12" name="Broadcast_143652" type="Broadcast" version="opset3">
+			<data mode="numpy" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="ScatterNDUpdate_143653" type="ScatterNDUpdate" version="opset4">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>-1</dim>
+					<dim>2</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="ScatterNDUpdate_143653" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="input_ids">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="Result_143663" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+		<layer id="10" name="Result_143664" type="Result" version="opset1">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="3" to-port="1" />
+		<edge from-layer="1" from-port="0" to-layer="4" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
+		<edge from-layer="3" from-port="4" to-layer="4" to-port="1" />
+		<edge from-layer="3" from-port="3" to-layer="6" to-port="0" />
+		<edge from-layer="3" from-port="2" to-layer="8" to-port="1" />
+		<edge from-layer="3" from-port="3" to-layer="13" to-port="2" />
+		<edge from-layer="3" from-port="2" to-layer="13" to-port="1" />
+		<edge from-layer="3" from-port="4" to-layer="12" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="5" from-port="0" to-layer="7" to-port="0" />
+		<edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
+		<edge from-layer="7" from-port="2" to-layer="8" to-port="2" />
+		<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
+		<edge from-layer="9" from-port="1" to-layer="10" to-port="0" />
+		<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
+		<edge from-layer="12" from-port="2" to-layer="13" to-port="0" />
+		<edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
+		<edge from-layer="14" from-port="1" to-layer="15" to-port="0" />
+	</edges>
+	<rt_info>
+		<eos_token_id value="2" />
+	</rt_info>
+</net>

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}