Upload folder using huggingface_hub

README.md

@@ -1,135 +1,202 @@
 ---
 base_model: nicholasKluge/TeenyTinyLlama-460m
-library_name: transformers
-license: cc-by-nc-nd-4.0
-language:
-- pt
-pipeline_tag: text-generation
-datasets:
-- cnmoro/LogicReasoningEnglishPortuguese
-- LumiOpen/opengpt-x_gsm8kx
-metrics:
-- accuracy
+library_name: peft
 ---
-# 🧠 WNL468M — Modelo de Raciocínio Lógico em Português para Ensino e Educação
 
-**WNL268M** é um modelo de linguagem com aproximadamente **268 milhões de parâmetros**, desenvolvido especialmente para tarefas de **raciocínio lógico** e compreensão em **português**, com foco em **ensino, educação e suporte acadêmico**. Este projeto foi inspirado e criado para um **projeto acadêmico** de destaque em uma **feira de ciências**, com o objetivo de contribuir para o avanço do ensino de inteligência artificial aplicada ao idioma português.
+# Model Card for Model ID
 
-## ✨ Origem do Nome
+<!-- Provide a quick summary of what the model is/does. -->
 
-**WNL** é uma homenagem a três colegas que foram a inspiração inicial para o projeto:
 
-- **W** — Weia  
-- **N** — Nauria  
-- **L** — Leonilda  
 
-Embora elas não participem diretamente, seus nomes simbolizam a motivação que deu origem ao desenvolvimento do modelo.
+## Model Details
 
-## 👥 Equipe Fundadora
+### Model Description
 
-- Marius Jabami – Desenvolvedor principal, integração com modelo, lógica central e liderança técnica
+<!-- Provide a longer summary of what this model is. -->
 
-- Ilson Lopes – Apoio geral ao desenvolvimento e testes técnicos
 
-- Délcio Pro – Interface visual (Kivy), processamento de texto, usabilidade
 
-- José Bukete – Lógica do chat em Kivy, controle de eventos e exibição de mensagens
+- **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]
 
-- Fernando Queta – Integração com modelo Transformers, geração de respostas
+### Model Sources [optional]
 
-- Inácio Oicani – Histórico de conversa, normalização de texto, refinamento de UI/UX
+<!-- Provide the basic links for the model. -->
 
-- Daniel Raimundo – Estilo visual, fontes, cores, animações e experiência do usuário
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
 
-- Celsio Simplício – Testes, simulações, depuração e melhoria de desempenho
+## Uses
 
-- Arsênio Afonso – Suporte em testes e revisão técnica
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-- Cristiano Jomba – Testes diversos, análise de comportamento do chatbot
+### Direct Use
 
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-## 🧩 Dataset Utilizado
+[More Information Needed]
 
-O modelo foi finamente ajustado utilizando o dataset:
+### Downstream Use [optional]
 
-📚 [`cnmoro/LogicReasoningEnglishPortuguese`](https://huggingface.co/datasets/cnmoro/LogicReasoningEnglishPortuguese)
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
-Este conjunto bilíngue contém pares de perguntas e respostas que exigem **raciocínio lógico**, proporcionando uma base robusta para treinar o modelo em tarefas de compreensão, dedução e resposta estruturada, essenciais para aplicações educacionais.
+[More Information Needed]
 
-## 🔍 Informações Técnicas Detalhadas
+### Out-of-Scope Use
 
-- **Parâmetros:** ~468 milhões  
-- **Arquitetura Base:** Adaptada do LLaMA, conhecida pela eficiência em tarefas de linguagem natural  
-- **Tokenizador:** SentencePiece (formato LLaMA)  
-- **Método de Treinamento:** Fine-tuning com LoRA, seguido de mesclagem dos pesos para otimização  
-- **Framework:** PyTorch com Hugging Face Transformers  
-- **Tipo de Modelo:** Causal Language Model (modelo generativo para texto)  
-- **Idiomas:** Português (principal), com suporte a dados em inglês do dataset bilíngue  
-- **Uso:** Aplicações educacionais, chatbots acadêmicos, ferramentas de ensino e suporte ao raciocínio lógico  
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-## 🎯 Propósito e Aplicações
+[More Information Needed]
 
-O **WNL268M** foi desenvolvido com foco pedagógico, visando:
+## Bias, Risks, and Limitations
 
-- Facilitar o aprendizado e o ensino de lógica e raciocínio no idioma português  
-- Servir como base para projetos acadêmicos e feiras de ciências, mostrando a viabilidade de modelos customizados para educação  
-- Criar ferramentas interativas que ajudem estudantes e educadores a explorarem conceitos complexos de forma acessível e inteligente  
-- Demonstrar que projetos de IA podem ser desenvolvidos colaborativamente em ambientes educacionais  
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-## 💻 Como Usar o Modelo
+[More Information Needed]
 
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
-import torch
+### Recommendations
 
-repo_id = "lambdaindie/WNL468M"
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-tokenizer = AutoTokenizer.from_pretrained(repo_id)
-model = AutoModelForCausalLM.from_pretrained(repo_id, device_map="auto", torch_dtype=torch.float16)
-model.eval()
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
-streamer = TextStreamer(tokenizer)
+## How to Get Started with the Model
 
-while True:
-    prompt = input("Você: ")
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    _ = model.generate(**inputs, max_new_tokens=100, streamer=streamer)
+Use the code below to get started with the model.
 
-```
+[More Information Needed]
 
-🚀 Próximos Passos
+## Training Details
 
-Ampliação do dataset com mais exemplos em português
+### Training Data
 
-Desenvolvimento de versões maiores com foco em domínio acadêmico específico
+<!-- 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. -->
 
-Integração com plataformas educacionais para testes reais em sala de aula
+[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]
 
-Criado com dedicação, conhecimento e fé no futuro da educação.
-Equipe fundadora empenhada em transformar aprendizado através da inteligência artificial.
+[More Information Needed]
 
----
 
-## 🔒 Licença
+#### 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. -->
 
-Este modelo está licenciado sob:
+[More Information Needed]
 
-**[CC BY-NC-ND 4.0 (Creative Commons Attribution-NonCommercial-NoDerivatives 4.0)](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.pt)**
+## More Information [optional]
 
-Você é livre para:
+[More Information Needed]
 
-- Compartilhar — copiar e redistribuir o material em qualquer meio ou formato
+## Model Card Authors [optional]
 
-Desde que siga os termos:
+[More Information Needed]
 
-- **Atribuição** — Deve creditar os autores (ver seção "Equipe Fundadora").
-- **Não Comercial** — Não pode usar o material para fins comerciais.
-- **Sem Derivações** — Não pode remixar, transformar ou criar a partir do material.
+## Model Card Contact
 
-Este modelo é exclusivo para fins **acadêmicos e educacionais**.
+[More Information Needed]
+### Framework versions
 
----
+- PEFT 0.15.2

adapter_config.json

@@ -24,8 +24,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25edca5a6d7ddef8b3e30502982709a0b20a24cbd2d50169477550e925c01ca
+oid sha256:d0568795f5ce5198768994f32e4445d3352141cf2c84e5347ad9471e73bee7be
 size 3158328

checkpoint-11/README.md

@@ -0,0 +1,202 @@
+---
+base_model: nicholasKluge/TeenyTinyLlama-460m
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-11/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nicholasKluge/TeenyTinyLlama-460m",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-11/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0568795f5ce5198768994f32e4445d3352141cf2c84e5347ad9471e73bee7be
+size 3158328

checkpoint-11/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2f1cf3b58bf69e0d674a9f68b0f6d14a331b8dc53d8b96e8916b5a4f662e37
+size 6372346

checkpoint-11/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936e1ac437536fc6f2a7523589c813bc4d123da5ed918bb367718a11bad5f91c
+size 14244

checkpoint-11/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade215a47a020920d715bac0324c23ef8689acd1f3b55b0400999cc5a8b8c5b9
+size 1064

checkpoint-11/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-11/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "bos_token_id": 1,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "pad_token_id": 2,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "unk_token_id": 0,
+  "use_default_system_prompt": false
+}

checkpoint-11/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 11,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.0843924954533577,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 2.6615,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 11,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 139379129450496.0,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-11/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24fb5154f80d1216ede6ffde394af20cc4d50dcf55981571384984bbf0cc8293
+size 5240

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 2,
+    "pad_type_id": 0,
+    "pad_token": "</s>"
+  },
   "added_tokens": [
     {
       "id": 0,