Update MagistrTheOne/RadonSAI - add YAML metadata, developing status, and transformers registration

README.md

@@ -1,48 +1,74 @@
 ---
 license: apache-2.0
+language:
+- ru
+- en
 tags:
 - radon
-- gpt2
-- working
-- 1024d
+- russian
+- english
+- developing
+- mistral
+- 2b
+- quantized
+pipeline_tag: text-generation
+library_name: transformers
+model_status: developing
+base_model: mistralai/Mistral-7B-v0.1
+size_categories: 3B
+model-index:
+- name: RadonSAI
+  results: []
 ---
 
-# RadonSAI (Working)
 
-Полностью рабочая версия RadonSAI с реальными весами.
+# RadonSAI
 
-## Технические характеристики
-- Параметры: ~203,668,480
-- Размерность: 1024
-- Слои: 12
-- Головы внимания: 16
+## Model Description
+
+RadonSAI is a 2B parameters transformer model designed for main RADON model in the RADON ecosystem.
+
+### Key Features
+
+- **Parameters**: 2B parameters
+- **Base Model**: mistralai/Mistral-7B-v0.1
+- **Status**: Developing
+- **Languages**: Russian, English
+- **Architecture**: GPT2-based
+
+## Usage
 
-## Использование
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
+# Load model
 model = AutoModelForCausalLM.from_pretrained("MagistrTheOne/RadonSAI")
 tokenizer = AutoTokenizer.from_pretrained("MagistrTheOne/RadonSAI")
 
-# Генерация текста
-input_text = "Hello, how are you?"
-inputs = tokenizer(input_text, return_tensors="pt")
-outputs = model.generate(**inputs, max_length=50)
+# Generate text
+prompt = "Привет, как дела?"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=100, temperature=0.7)
 result = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(result)
 ```
 
-## Тестирование
-```python
-# Быстрый тест
-import torch
-model = AutoModelForCausalLM.from_pretrained("MagistrTheOne/RadonSAI")
-tokenizer = AutoTokenizer.from_pretrained("MagistrTheOne/RadonSAI")
+## Model Status
 
-# Простая генерация
-text = "The future of AI is"
-inputs = tokenizer(text, return_tensors="pt")
-with torch.no_grad():
-    outputs = model.generate(**inputs, max_length=30, do_sample=True, temperature=0.7)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-```
+**Status**: Developing
+**Last Updated**: 2025-10-08
+**Creator**: MagistrTheOne
+
+## License
+
+Apache 2.0 License
+
+## Contact
+
+- GitHub: [MagistrTheOne/Radon2BMistral](https://github.com/MagistrTheOne/Radon2BMistral)
+- Hugging Face: [MagistrTheOne/RadonSAI](https://huggingface.co/MagistrTheOne/RadonSAI)
+- Creator: [MagistrTheOne](https://github.com/MagistrTheOne)
+
+---
+
+**Created with ❤️ by MagistrTheOne**

config.json

@@ -1,31 +1,34 @@
 {
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "model_name": "radonsai",
+  "model_type": "mistral",
+  "vocab_size": 32000,
+  "hidden_size": 2048,
+  "num_layers": 24,
+  "num_attention_heads": 32,
+  "num_kv_heads": 8,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 32768,
+  "sliding_window": 4096,
+  "rope_theta": 10000.0,
+  "rms_norm_eps": 1e-06,
+  "dropout": 0.1,
+  "attention_dropout": 0.1,
+  "activation_function": "silu",
+  "layer_norm_eps": 1e-06,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_embd": 1024,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
   "use_cache": true,
-  "vocab_size": 50257
-}
+  "torch_dtype": "float32",
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "status": "developing",
+  "last_updated": "2025-10-08",
+  "transformers_version": "4.36.0",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "auto_map": {
+    "AutoModelForCausalLM": "models.mistral_model.MistralForCausalLM"
+  },
+  "creator": "MagistrTheOne",
+  "description": "RADON: 2B parameter model adapted from Mistral-7B"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4cb54b9ebcdc8a72ebb3265c871023c38189e7d6851a87641fe6aeafce66ca
-size 814689096
+oid sha256:3323be5474d086a52bf5c73dee21b5438b501c1f4b007342edbe6cada51e25c9
+size 131278312

model_card.yml

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+language:
+- ru
+- en
+tags:
+- radon
+- russian
+- english
+- developing
+- mistral
+- 2b
+- quantized
+pipeline_tag: text-generation
+library_name: transformers
+model_status: developing
+base_model: mistralai/Mistral-7B-v0.1
+size_categories: 3B
+model-index:
+- name: RadonSAI
+  results: []
+---

special_tokens_map.json

@@ -13,7 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -12,11 +12,12 @@
     }
   },
   "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
+  "pad_token": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }