Add arabert-lora v1 logged-model subtree (pyfunc bundle)

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/MLmodel

@@ -0,0 +1,39 @@
+artifact_path: /Users/prajnashetty/Workspace/Arabic Sentiment Analysis/app/mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts
+flavors:
+  python_function:
+    artifacts:
+      backend_type:
+        path: artifacts/pyfunc_meta.json
+        uri: models/arabert-lora-v1/pyfunc_meta.json
+      model_dir:
+        path: artifacts/arabert-lora-v1
+        uri: models/arabert-lora-v1
+    cloudpickle_version: 3.1.2
+    code: null
+    env:
+      conda: conda.yaml
+      virtualenv: python_env.yaml
+    loader_module: mlflow.pyfunc.model
+    python_model: python_model.pkl
+    python_version: 3.12.8
+    streamable: false
+is_signature_from_type_hint: false
+mlflow_version: 3.12.0
+model_id: m-f9cac40424504a5a91d9449f38f5bd7c
+model_size_bytes: 547201599
+model_uuid: m-f9cac40424504a5a91d9449f38f5bd7c
+prompts: null
+run_id: 94cccbd929a845dd9e47d46a5c3db759
+saved_input_example_info:
+  artifact_path: input_example.json
+  pandas_orient: split
+  serving_input_path: serving_input_example.json
+  type: dataframe
+signature:
+  inputs: '[{"type": "string", "name": "text", "required": true}]'
+  outputs: '[{"type": "string", "name": "text", "required": true}, {"type": "string",
+    "name": "sentiment", "required": true}, {"type": "double", "name": "confidence",
+    "required": true}]'
+  params: null
+type_hint_from_example: false
+utc_time_created: '2026-05-22 18:09:03.492031'

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/artifacts/arabert-lora-v1/README.md

@@ -0,0 +1,206 @@
+---
+base_model: aubmindlab/bert-base-arabertv2
+library_name: peft
+tags:
+- base_model:adapter:aubmindlab/bert-base-arabertv2
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/artifacts/arabert-lora-v1/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "aubmindlab/bert-base-arabertv2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/artifacts/arabert-lora-v1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ede973351e6bf26581ffbf3c00513ea563be855ed41e1c8165343b4fae91178
+size 1195748

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/artifacts/arabert-lora-v1/labels.json

@@ -0,0 +1 @@
+["positive", "negative", "neutral"]

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/artifacts/arabert-lora-v1/pyfunc_meta.json

@@ -0,0 +1 @@
+{"backend_type": "arabert-lora"}

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/artifacts/arabert-lora-v1/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "+ك",
+    "+كما",
+    "ك+",
+    "+وا",
+    "+ين",
+    "و+",
+    "+كن",
+    "+ان",
+    "+هم",
+    "+ة",
+    "[بريد]",
+    "لل+",
+    "+ي",
+    "+ت",
+    "+ن",
+    "س+",
+    "ل+",
+    "[مستخدم]",
+    "+كم",
+    "+ا",
+    "ب+",
+    "ف+",
+    "+نا",
+    "+ها",
+    "+ون",
+    "+هما",
+    "ال+",
+    "+ه",
+    "+هن",
+    "+ات",
+    "[رابط]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/artifacts/pyfunc_meta.json

@@ -0,0 +1 @@
+{"backend_type": "arabert-lora"}

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/conda.yaml

@@ -0,0 +1,30 @@
+channels:
+- conda-forge
+dependencies:
+- python=3.12.8
+- pip
+- pip:
+  - mlflow==3.12.0
+  - annotated-doc==0.0.4
+  - annotated-types==0.7.0
+  - anyio==4.13.0
+  - click==8.4.0
+  - cloudpickle==3.1.2
+  - colorama==0.4.6; sys_platform == "win32"
+  - fastapi==0.136.1
+  - h11==0.16.0
+  - httptools==0.7.1
+  - idna==3.15
+  - pydantic-core==2.46.4
+  - pydantic==2.13.4
+  - python-dotenv==1.2.2
+  - pyyaml==6.0.3
+  - starlette==0.52.1
+  - typing-extensions==4.15.0
+  - typing-inspection==0.4.2
+  - uvicorn==0.47.0
+  - uvloop==0.22.1; platform_python_implementation != "PyPy" and sys_platform != "cygwin"
+    and sys_platform != "win32"
+  - watchfiles==1.2.0
+  - websockets==16.0
+name: mlflow-env

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/input_example.json

@@ -0,0 +1 @@
+{"columns": ["text"], "data": [["\u0645\u0631\u062d\u0628\u0627"]]}

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/pyproject.toml

@@ -0,0 +1,46 @@
+[project]
+name = "arabic-sentiment-mlops"
+version = "0.1.0"
+requires-python = ">=3.12"
+dependencies = [
+    "fastapi>=0.115",
+    "uvicorn[standard]>=0.30",
+    "pydantic>=2.7",
+]
+
+[project.optional-dependencies]
+ml = [
+    "transformers>=4.40",
+    "catboost>=1.2",
+    "scikit-learn>=1.5",
+    "mlflow>=2.14",
+    "torch>=2.3",
+    "datasets>=2.18",
+    "peft>=0.11",
+    "accelerate>=0.30",
+    "evaluate>=0.4",
+]
+dev = [
+    "pytest>=8.2",
+    "pytest-cov>=5.0",
+    "httpx>=0.27",
+    "ruff>=0.4",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/sentiment", "src/api"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py312"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "N", "UP"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/python_env.yaml

@@ -0,0 +1,7 @@
+python: 3.12.8
+build_dependencies:
+- pip
+- setuptools==81.0.0
+- wheel
+dependencies:
+- -r requirements.txt

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/python_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0b2a47bd17bef43bde1711327fcec21e5427d2d19f96ceb96afec73431bb53
+size 544321244

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/registered_model_meta

@@ -0,0 +1,2 @@
+model_name: arabert-lora
+model_version: '1'

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/requirements.txt

@@ -0,0 +1,22 @@
+mlflow==3.12.0
+annotated-doc==0.0.4
+annotated-types==0.7.0
+anyio==4.13.0
+click==8.4.0
+cloudpickle==3.1.2
+colorama==0.4.6; sys_platform == "win32"
+fastapi==0.136.1
+h11==0.16.0
+httptools==0.7.1
+idna==3.15
+pydantic-core==2.46.4
+pydantic==2.13.4
+python-dotenv==1.2.2
+pyyaml==6.0.3
+starlette==0.52.1
+typing-extensions==4.15.0
+typing-inspection==0.4.2
+uvicorn==0.47.0
+uvloop==0.22.1; platform_python_implementation != "PyPy" and sys_platform != "cygwin" and sys_platform != "win32"
+watchfiles==1.2.0
+websockets==16.0

mlruns/1/models/m-f9cac40424504a5a91d9449f38f5bd7c/artifacts/serving_input_example.json

@@ -0,0 +1,12 @@
+{
+  "dataframe_split": {
+    "columns": [
+      "text"
+    ],
+    "data": [
+      [
+        "\u0645\u0631\u062d\u0628\u0627"
+      ]
+    ]
+  }
+}