Upload folder using huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+license_link: https://choosealicense.com/licenses/apache-2.0/
+---
+# falcon-7b-instruct-int8-ov
+* Model creator: [Tiiuae](https://huggingface.co/tiiuae)
+ * Original model: [falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct)
+
+## Description
+This is [falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT8 by [NNCF](https://github.com/openvinotoolkit/nncf).
+
+## Quantization Parameters
+
+Weight compression was performed using `nncf.compress_weights` with the following parameters:
+
+* mode: **int8_asym**
+* ratio: **1**
+
+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/falcon-7b-instruct-int8-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 [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/tiiuae/falcon-7b-instruct).
+
+## 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 +1,40 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b-instruct",
+  "activation": "gelu",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_falcon.FalconConfig",
+    "AutoModel": "modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "ffn_hidden_size": 18176,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "num_ln_in_parallel_attn": null,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778933886dcad6ca6803f150a1263de4438fb097ca5e36482cf3702ada46c734
+size 6926930384

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,118 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}