初始化项目，由ModelHub XC社区提供模型

Model: oguzatas/mamba-tr-project-transformer
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
+OguzhanAtasHW[[:space:]]state-space-models[[:space:]]on[[:space:]]Morphologically[[:space:]]Rich[[:space:]]Languages.pdf filter=lfs diff=lfs merge=lfs -text

OguzhanAtasHW state-space-models on Morphologically Rich Languages.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228f8128e9d9688a6682e7afc9bb8fab5ce4e0461ee9a86a3cf2e0223be71e49
+size 222951

README.md

@@ -0,0 +1,45 @@
+---
+license: mit
+language:
+- tr
+pipeline_tag: text-generation
+tags:
+- transformer
+- gpt2
+- turkish
+- baseline
+links:
+  - label: "Experiment Paper"
+    url: "https://huggingface.co/oguzatas/mamba-tr-project-transformer/resolve/main/OguzhanAtasHW%20state-space-models%20on%20Morphologically%20Rich%20Languages.pdf"
+---
+---
+
+[![Paper](https://img.shields.io/badge/PDF-Technical_Paper-red?style=for-the-badge&logo=adobeacrobatreader&logoColor=white)](https://huggingface.co/oguzatas/mamba-tr-project-transformer/resolve/main/OguzhanAtasHW%20state-space-models%20on%20Morphologically%20Rich%20Languages.pdf)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1UbkR-i3P6X2cFVWXlntySjki_WBdg0ac?usp=sharing)
+# Transformer Baseline (GPT-2 Style) - Turkish
+
+This model serves as the **baseline** for a comparative study between Transformer and Mamba architectures on agglutinative languages (specifically Turkish). It is a decoder-only Transformer model (~111M parameters) trained on the Turkish Wikipedia dataset.
+
+## Model Description
+- **Architecture:** GPT-2 (Small)
+- **Parameters:** ~111 Million
+- **Context Length:** 1024
+- **Training Data:** Turkish Wikipedia (Nov 2023)
+- **Purpose:** To provide a performance benchmark for the Mamba architecture.
+
+## Usage
+
+```python
+from transformers import GPT2LMHeadModel, PreTrainedTokenizerFast
+
+model_id = "oguzatas/mamba-tr-project-transformer"
+tokenizer_id = "oguzatas/mamba-tr-project-tokenizer"
+
+tokenizer = PreTrainedTokenizerFast.from_pretrained(tokenizer_id)
+model = GPT2LMHeadModel.from_pretrained(model_id)
+
+text = "Türkiye'nin başkenti"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=20)
+
+print(tokenizer.decode(outputs[0]))

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "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,
+  "transformers_version": "4.57.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 0,
+  "transformers_version": "4.57.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd6af4df74c6e106447f227074e19c64864e01f6e80fc67daa0712b4db62560
+size 441688704

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b5d2fa26807657660dda789e49098cf0c942e0e2f395baea285b0d17768f49
+size 5432