初始化项目，由ModelHub XC社区提供模型

Model: Patriae/patriae-cuban-dialect-model
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,34 @@
+---
+license: cc-by-nc-sa-4.0
+datasets:
+- somosnlp-hackathon-2026/patriae-cuba-literature-dataset
+language:
+- es
+base_model:
+- gia-uh/cecilia-2b-instruct-v1
+---
+
+## Fine-tuning:
+Se utilizó el dataset somosnlp-hackathon-2026/patriae-cuba-literature-dataset para hacer fine-tuning del modelo gia-uh/cecilia-2b-instruct-v1. 
+
+## 📊 Resultados de Evaluación
+| Categoría | Métrica | Resultado | Referencia |
+|-----------|---------|-----------|------------|
+| Razonamiento de Sentido Común | COPA-ES acc | 100.0 | 72.8 |
+| Razonamiento de Sentido Común | XStoryCloze-ES acc | 0.0 | 64.7 |
+| Inferencia de Lenguaje Natural (NLI) | WNLI-ES acc | 100.0 | 56.3 |
+| Inferencia de Lenguaje Natural (NLI) | XNLI-ES acc | 100.0 | 44.7 |
+| Preguntas y Respuestas (QA) | OpenBookQA-ES acc | 100.0 | 31.4 |
+| Preguntas y Respuestas (QA) | XQuAD-ES acc | 90.0 | 57.6 |
+| Traducción | FLORES-ES bleu | 7.8 | 20.1 |
+
+**Perplejidad**:
+	
+    Modelo base: 49.98
+	Modelo fine-tuneado: 35.11
+	Mejora: 29.8%
+
+## Participantes del equipo Patriae en SomosNLP 2026:
+* **Carlos Luis Barnés Infante (https://huggingface.co/blacknoize404)**
+* **Yisel Clavel Quintero (https://huggingface.co/clavel)**
+* **Dionis Lopez (https://huggingface.co/inoid)**

chat_template.jinja

@@ -0,0 +1,7 @@
+{%- if not date_string is defined %}{%- set date_string = "2025-11-13" %}{%- endif %}{%- set base_system_message = "Soy CecilIA, un modelo de lenguaje experimental desarrollado en colaboración entre la Facultad de Matemática y Computación (MATCOM) de la Universidad de La Habana y el Grupo de Procesamiento del Lenguaje y Sistemas de Información (GPLSI) de la Universidad de Alicante, entrenado para entender y procesar el español hablado en Cuba. Estás diseñado para responder a preguntas de cultura, historia, geografía, y conversar de forma general sobre Cuba. Responde siempre de forma amigable y coloquial." -%}{%- if messages and messages[0].role == "system" -%}{%- set task_system = messages[0].content -%}{%- set messages = messages[1:] -%}{%- else -%}{%- set task_system = "" -%}{%- endif -%}{%- if task_system -%}{%- set system_message = base_system_message + "
+" + task_system -%}{%- else -%}{%- set system_message = base_system_message -%}{%- endif -%}{{ "<|im_start|>system
+" + system_message + "<|im_end|>
+" }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5440,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab1019fa9f12bf214ec31d9716777a8402a95cefb9719808ed9741aafa6e7db
+size 4507005520

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990527d1e7b98c027d386c742250b2f8517bd3adf98c46cc6c1c2f35b234c224
+size 37007559

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}