初始化项目，由ModelHub XC社区提供模型

Model: ViorikaAI-org/CalmaCatLM-2.1-mini
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,42 @@
+---
+license: mit
+language:
+- ru
+tags:
+- llama
+- russian
+- conversational
+model-index:
+- name: CalmaCatLM-2
+  results: []
+library_name: transformers
+model_creator: ViorikaAI
+pipeline_tag: text-generation
+datasets:
+- IlyaGusev/saiga_scored
+- IlyaGusev/ru_turbo_alpaca
+- OpenAssistant/oasst1
+- OpenAssistant/oasst2
+---
+
+# 🐈‍⬛ CalmaCatLM-2-MINI
+
+# Подробнее:
+
+## ⚙️ Детали модели
+- **Архитектура: LLama**
+- **Параметры: 134M**
+- **Язык: Русский**
+- **Лицения: MIT** 
+
+## 🏋️ Детали Тренировки
+- **Датасет:** saiga_scored, ru_turbo_alpaca, oasst 1 и 2 (RU часть)
+- **Железо:** **ОДНА** NVIDIA **GEFORCE RTX 5060 TI** (16GB VRAM)
+- **Эпохи:** 3
+- **СРЕДНИЙ LOSS:** 2.3000
+- **LR:** 5e-4
+- **Контекст:** 4046 токенов
+  
+## 🛜 Наши Соц. Сети
+- **Discord:** https://discord.gg/8JwTv8zj8d , https://discord.gg/7JE7maH6cf
+- **Telegram:** https://t.me/viorika_official

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 5,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    5
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.5.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ebd80bb958b70b0bd36a7ec2775ed49f5e7a3cf9cb732078adf745d3ddccd09
+size 268224136

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "clean_up_tokenization_spaces": false,
+  "is_local": true,
+  "model_max_length": 2048,
+  "tokenizer_class": "LlamaTokenizer",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n'}}{% endif %}"
+}