Upload folder using huggingface_hub

README.md

@@ -1,3 +1,42 @@
+# Braindler Final Model v2
+
+Модель fine-tuned на датасетах:
+
+## Датасеты
+
+1. **mozgach_trener** (97 примеров)
+   - Образовательный контент на русском
+   - Алфавит, цифры, цвета, фигуры
+   
+2. **alice_gift** (175 примеров)  
+   - Дополнительные текстовые данные
+
+## Статистика обучения
+
+- Всего примеров: 163
+- Эпох: 3
+- Базовая модель: nativemind/braindler_full_trained_model
+- Дата: 2025-10-20
+
+## Использование
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("nativemind/braindler_final_model")
+tokenizer = AutoTokenizer.from_pretrained("nativemind/braindler_final_model")
+
+prompt = "User: Как произносится буква А?\nAssistant:"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=200)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Контакты
+
+- Email: [email protected]
+- HuggingFace: nativemind
+
 ---
-license: other
----
+
+© 2025 NativeMind. NativeMindNONC License (Non-Commercial)

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50257
+}

checkpoint-63/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50257
+}

checkpoint-63/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "pad_token_id": 50256,
+  "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,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-63/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.57.1"
+}

checkpoint-63/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73591f7ce750a0311c34b1df4786b518c9572221946c720bcdfe3c6e008c79d6
+size 500919936

checkpoint-63/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01b5b8fc9251d9b7a4cb057ed0cf3a571b32d53238b0725693efcc76aa72fd8
+size 1001930059

checkpoint-63/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455

checkpoint-63/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f73c3c949615fb2676a2b8bd33b0db09e91443fdef6758c35d52283c70c984
+size 1465

checkpoint-63/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-63/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-63/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 22.141286849975586,
+      "learning_rate": 4.5e-06,
+      "loss": 6.0086,
+      "step": 10
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 10.527143478393555,
+      "learning_rate": 9.5e-06,
+      "loss": 3.7945,
+      "step": 20
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 6.946624755859375,
+      "learning_rate": 1.45e-05,
+      "loss": 2.2198,
+      "step": 30
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 4.248944282531738,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 1.037,
+      "step": 40
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 4.16041898727417,
+      "learning_rate": 2.45e-05,
+      "loss": 0.5752,
+      "step": 50
+    },
+    {
+      "epoch": 2.8780487804878048,
+      "grad_norm": 4.716129302978516,
+      "learning_rate": 2.95e-05,
+      "loss": 0.5495,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 63,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 127771803648000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-63/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad309489338449cc67dfe9f76e6e22e6fa0c44e04ced7c761f99df78923df318
+size 5777

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "pad_token_id": 50256,
+  "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,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73591f7ce750a0311c34b1df4786b518c9572221946c720bcdfe3c6e008c79d6
+size 500919936

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad309489338449cc67dfe9f76e6e22e6fa0c44e04ced7c761f99df78923df318
+size 5777