Auto-upload: модель обучена через CI/CD

.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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

2_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 768,
+    "out_features": 3072,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffbd357e603d1635ea0ffb287ac4d6b640e8410cef9392bbce696809229b2520
+size 9437272

3_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 3072,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144adf0dcbf3552f465aa5d893d42b0d81eac5c9e2d1dd8f4a8b0b354cbf88fb
+size 9437272

README.md

@@ -1,132 +1,226 @@
----
-library_name: setfit
-tags:
-- setfit
-- sentence-transformers
-- classification
-- russian
-- voice-commands
-- panda
-- commands
-language: ru
-license: mit
-pipeline_tag: text-classification
----
-# CVC-Panda
-
-Модель для классификации голосовых команд на русском языке для управления пандой (CVC-Panda).
-
-## Описание
-
-Эта модель представляет собой SetFit классификатор, обученный для распознавания и классификации голосовых команд на русском языке. Модель использует few-shot learning подход через SetFit, что позволяет эффективно обучаться на небольшом количестве примеров.
-
-## Использование
-
-### Базовое использование
-
-```python
-from setfit import SetFitModel
-
-# Загрузка модели
-model = SetFitModel.from_pretrained("your-username/cvc-panda-commands", token="your_token")
-
-# Классификация команд
-commands = ["равняйся", "отставить", "налево", "направо"]
-predictions = model(commands)
-
-# Получение вероятностей
-probs = model.predict_proba(commands)
-```
-
-### Использование с токеном
-
-Если модель приватная или требует аутентификации:
-
-```python
-from setfit import SetFitModel
-from huggingface_hub import login
-
-# Авторизация
-login(token="your_hf_token")
-
-# Загрузка модели
-model = SetFitModel.from_pretrained("your-username/cvc-panda-commands")
-```
-
-### Пакетная обработка
-
-```python
-from setfit import SetFitModel
-
-model = SetFitModel.from_pretrained("your-username/cvc-panda-commands", token="your_token")
-
-# Обработка списка команд
-commands = [
-    "равняйся",
-    "отставить", 
-    "налево",
-    "направо",
-    "шагом марш"
-]
-
-predictions = model(commands)
-print(predictions)
-```
-
-## Архитектура модели
-
-Модель основана на SetFit и использует архитектуру sentence-transformers:
-
-- **Базовый энкодер**: Предобученная модель для русского языка
-- **Классификатор**: Обученная голова классификатора (SetFit head)
-- **Формат**: SetFit/sentence-transformers совместимый формат
-
-## Обучение
-
-Модель обучена на датасете голосовых команд с использованием SetFit (few-shot learning). Обучение происходит автоматически через CI/CD пайплайн, после чего модель загружается на Hugging Face Hub.
-
-### Параметры обучения
-
-- **Метод**: SetFit (few-shot learning)
-- **Язык**: Русский (ru)
-- **Тип задачи**: Многоклассовая классификация
-
-## Структура модели
-
-Модель сохраняется в формате sentence-transformers и содержит:
-
-- `config.json` - Основная конфигурация модели
-- `config_setfit.json` - Конфигурация SetFit
-- `config_sentence_transformers.json` - Конфигурация sentence-transformers
-- `model_head.pkl` - Обученная голова классификатора
-- `model.safetensors` - Веса модели
-- `tokenizer.json` - Токенизатор
-- Модули: `1_Pooling/`, `2_Dense/`, `3_Dense/`, `4_Normalize/`
-
-## Версионирование
-
-Модель автоматически версионируется через Git при каждой загрузке через CI/CD. Вы можете:
-
-- Просматривать историю версий на вкладке "Files and versions"
-- Использовать конкретную версию через commit hash
-- Тегировать стабильные версии для production
-
-## Требования
-
-```python
-setfit>=0.7.0
-sentence-transformers>=2.2.0
-transformers>=4.21.0
-```
-
-## Лицензия
-
-MIT License
-
-## Автор
-
-ShiWarai
-
----
-
-**Примечание**: Для приватных моделей убедитесь, что токен `HF_TOKEN` установлен на production-сервере.
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: робот не любит бегать
+- text: надо равняться
+- text: панда ложись
+- text: ну остановись
+- text: беги бы
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: setfit
+inference: true
+base_model: google/embeddinggemma-300M
+model-index:
+- name: SetFit with google/embeddinggemma-300M
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.890282131661442
+      name: Accuracy
+---
+
+# SetFit with google/embeddinggemma-300M
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [google/embeddinggemma-300M](https://huggingface.co/google/embeddinggemma-300M) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+
+The model has been trained using an efficient few-shot learning technique that involves:
+
+1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
+2. Training a classification head with features from the fine-tuned Sentence Transformer.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SetFit
+- **Sentence Transformer body:** [google/embeddinggemma-300M](https://huggingface.co/google/embeddinggemma-300M)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 2048 tokens
+- **Number of Classes:** 13 classes
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
+- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
+- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
+
+### Model Labels
+| Label              | Examples                                                                                                                      |
+|:-------------------|:------------------------------------------------------------------------------------------------------------------------------|
+| unknown            | <ul><li>'чей робот'</li><li>'опять лежать'</li><li>'смотри панда'</li></ul>                                                   |
+| stand_at_attention | <ul><li>'пора выравняться'</li><li>'не хочешь равняться'</li><li>'выравнялся бы'</li></ul>                                    |
+| dismiss            | <ul><li>'давай поднимись'</li><li>'пора подняться'</li><li>'эй встань'</li></ul>                                              |
+| silence            | <ul><li>'перестать говорить'</li><li>'перестаньте болтать'</li><li>'замолкать'</li></ul>                                      |
+| rotate             | <ul><li>'переворачиваться'</li><li>'кувыркнись'</li><li>'ты кувыркайся'</li></ul>                                             |
+| give_paw           | <ul><li>'ну лапу дай'</li><li>'хотела бы чтобы панда дала лапу'</li><li>'панда давай лапу'</li></ul>                          |
+| stop_running       | <ul><li>'а ну остановись'</li><li>'смирно'</li><li>'попроси робота остановиться'</li></ul>                                    |
+| reconnect_joystick | <ul><li>'не хочешь подключить джойстик'</li><li>'подключись к джойстику сейчас'</li><li>'можно подключить джойстик'</li></ul> |
+| bind               | <ul><li>'привязывать робота'</li><li>'панда привяжи панду'</li><li>'привяжите робота'</li></ul>                               |
+| unbind             | <ul><li>'панда отвяжи панду'</li><li>'отвяжешь панду'</li><li>'отвяжи панду панда'</li></ul>                                  |
+| lie_down           | <ul><li>'быстро ложись'</li><li>'упасть'</li><li>'полежи'</li></ul>                                                           |
+| run                | <ul><li>'надо бежать'</li><li>'побеги'</li><li>'хотела бы чтобы панда бежала'</li></ul>                                       |
+| help               | <ul><li>'надо помочь'</li><li>'помог бы'</li><li>'команды'</li></ul>                                                          |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.8903   |
+
+## Uses
+
+### Direct Use for Inference
+
+First install the SetFit library:
+
+```bash
+pip install setfit
+```
+
+Then you can load this model and run inference.
+
+```python
+from setfit import SetFitModel
+
+# Download from the 🤗 Hub
+model = SetFitModel.from_pretrained("tmplxrs3m7t/panda_commands")
+# Run inference
+preds = model("беги бы")
+```
+
+<!--
+### Downstream Use
+
+*List how someone could finetune this model on their own dataset.*
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Set Metrics
+| Training set | Min | Median | Max |
+|:-------------|:----|:-------|:----|
+| Word count   | 1   | 2.3697 | 7   |
+
+| Label              | Training Sample Count |
+|:-------------------|:----------------------|
+| bind               | 44                    |
+| dismiss            | 128                   |
+| give_paw           | 83                    |
+| help               | 18                    |
+| lie_down           | 88                    |
+| reconnect_joystick | 108                   |
+| rotate             | 109                   |
+| run                | 85                    |
+| silence            | 22                    |
+| stand_at_attention | 70                    |
+| stop_running       | 108                   |
+| unbind             | 30                    |
+| unknown            | 381                   |
+
+### Training Hyperparameters
+- batch_size: (128, 128)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 20
+- body_learning_rate: (2e-05, 2e-05)
+- head_learning_rate: 2e-05
+- loss: CosineSimilarityLoss
+- distance_metric: cosine_distance
+- margin: 0.25
+- end_to_end: False
+- use_amp: False
+- warmup_proportion: 0.1
+- l2_weight: 0.01
+- seed: 42
+- eval_max_steps: -1
+- load_best_model_at_end: False
+
+### Training Results
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0025 | 1    | 0.2328        | -               |
+| 0.1253 | 50   | 0.0955        | -               |
+| 0.2506 | 100  | 0.0228        | -               |
+| 0.3759 | 150  | 0.0098        | -               |
+| 0.5013 | 200  | 0.0044        | -               |
+| 0.6266 | 250  | 0.0031        | -               |
+| 0.7519 | 300  | 0.0031        | -               |
+| 0.8772 | 350  | 0.0022        | -               |
+
+### Framework Versions
+- Python: 3.11.14
+- SetFit: 1.1.3
+- Sentence Transformers: 5.2.1
+- Transformers: 4.57.6
+- PyTorch: 2.9.1+cu128
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## Citation
+
+### BibTeX
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+    doi = {10.48550/ARXIV.2209.11055},
+    url = {https://arxiv.org/abs/2209.11055},
+    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+    title = {Efficient Few-Shot Learning Without Prompts},
+    publisher = {arXiv},
+    year = {2022},
+    copyright = {Creative Commons Attribution 4.0 International}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,60 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3TextModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 3,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 257,
+  "transformers_version": "4.57.6",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 262144
+}

config_sentence_transformers.json

@@ -0,0 +1,26 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.1",
+    "transformers": "4.57.6",
+    "pytorch": "2.9.1+cu128"
+  },
+  "prompts": {
+    "query": "task: search result | query: ",
+    "document": "title: none | text: ",
+    "BitextMining": "task: search result | query: ",
+    "Clustering": "task: clustering | query: ",
+    "Classification": "task: classification | query: ",
+    "InstructionRetrieval": "task: code retrieval | query: ",
+    "MultilabelClassification": "task: classification | query: ",
+    "PairClassification": "task: sentence similarity | query: ",
+    "Reranking": "task: search result | query: ",
+    "Retrieval": "task: search result | query: ",
+    "Retrieval-query": "task: search result | query: ",
+    "Retrieval-document": "title: none | text: ",
+    "STS": "task: sentence similarity | query: ",
+    "Summarization": "task: summarization | query: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

config_setfit.json

@@ -0,0 +1,18 @@
+{
+  "labels": [
+    "bind",
+    "dismiss",
+    "give_paw",
+    "help",
+    "lie_down",
+    "reconnect_joystick",
+    "rotate",
+    "run",
+    "silence",
+    "stand_at_attention",
+    "stop_running",
+    "unbind",
+    "unknown"
+  ],
+  "normalize_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a48b877b051dfd0d0f3db30d4902e9f7b400ad1f4baac77157f8af3d385b41d
+size 1211486072

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7c402de572d9f0275e22adf98c74ad367409a904d425b229ea42b7d01888d0
+size 81743

modules.json

@@ -0,0 +1,32 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 2048,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "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 sha256:216e2a79606fe879c9f17c529c71cd241338407fd5646b595ffd3c4b9ea1d503
+size 33385262