初始化项目，由ModelHub XC社区提供模型

Model: asafaya/kanarya-2b
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 +1,74 @@
+---
+license: apache-2.0
+datasets:
+- oscar
+- mc4
+language:
+- tr
+pipeline_tag: text-generation
+widget:
+- text: "Benim adım Zeynep, ve en sevdiğim kitabın adı:"
+  example_title: "Benim adım Zeynep, ve en sevdiğim kitabın adı"
+- text: "Bugünkü yemeğimiz"
+  example_title: "Bugünkü yemeğimiz"
+---
+
+# Kanarya-2B: Turkish Language Model
+
+<img src="https://asafaya.me/images/kanarya.webp" alt="Kanarya Logo" style="width:600px;"/>
+
+**Kanarya** is a pre-trained Turkish GPT-J 2B model. Released as part of [Turkish Data Depository](https://tdd.ai/) efforts, the Kanarya family has two versions (Kanarya-2B, Kanarya-0.7B). Kanarya-2B is the larger version and Kanarya-0.7B is the smaller version. Both models are trained on a large-scale Turkish text corpus, filtered from OSCAR and mC4 datasets. The training data is collected from various sources, including news, articles, and websites, to create a diverse and high-quality dataset. The models are trained using a JAX/Flax implementation of the [GPT-J](https://github.com/kingoflolz/mesh-transformer-jax) architecture.
+
+## Model Details
+
+- Model Name: Kanarya-2B
+- Model Size: 2,050M parameters
+- Training Data: OSCAR, mC4
+- Language: Turkish
+- Layers: 24
+- Hidden Size: 2560
+- Number of Heads: 20
+- Context Size: 2048
+- Positional Embeddings: Rotary
+- Vocabulary Size: 32,768
+
+## Intended Use
+
+This model is only pre-trained on Turkish text data and is intended to be fine-tuned on a wide range of Turkish NLP tasks. The model can be used for various Turkish NLP tasks, including text generation, translation, summarization, and other Turkish NLP tasks. This model is not intended to be used for any downstream tasks without fine-tuning.
+
+## Limitations and Ethical Considerations
+
+The model is trained on a diverse and high-quality Turkish text corpus, but it may still generate toxic, biased, or unethical content. It is highly recommended to use the model responsibly and make sure that the generated content is appropriate for the use case. Please use the model responsibly and report any issues.
+
+## License: Apache 2.0
+
+The model is licensed under the Apache 2.0 License. It is free to use for any purpose, including commercial use. We encourage users to contribute to the model and report any issues. However, the model is provided "as is" without warranty of any kind.
+
+## Citation
+
+If you use the model, please cite the following paper:
+
+```bibtex
+@inproceedings{safaya-etal-2022-mukayese,
+    title = "Mukayese: {T}urkish {NLP} Strikes Back",
+    author = "Safaya, Ali  and
+      Kurtulu{\c{s}}, Emirhan  and
+      Goktogan, Arda  and
+      Yuret, Deniz",
+    editor = "Muresan, Smaranda  and
+      Nakov, Preslav  and
+      Villavicencio, Aline",
+    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
+    month = may,
+    year = "2022",
+    address = "Dublin, Ireland",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2022.findings-acl.69",
+    doi = "10.18653/v1/2022.findings-acl.69",
+    pages = "846--863",
+}
+```
+
+## Acknowledgments
+
+During this work, Ali Safaya was supported by [KUIS AI Center](https://ai.ku.edu.tr/) fellowship. Moreover, the pre-training of these models were performed at TUBITAK ULAKBIM, High Performance and Grid Computing Center ([TRUBA](https://www.truba.gov.tr/index.php/en/main-page/) resources).

config.json

@@ -0,0 +1,42 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.01,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "gptj",
+  "n_embd": 2560,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary": true,
+  "rotary_dim": 64,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 2048,
+      "temperature": 0.8,
+      "top_k": 50
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139a7664016cd5f5b6dbacdd7851cab0fc8d2a039f0d5bce14fa3ce25816b371
+size 4111363281

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.31.0",
+  "do_sample": true,
+  "temperature": 0.8,
+  "max_length": 2048,
+  "top_k": 50
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098e57c5cbe3a15c84945f4dee90118c454db7e22904a01972cfda477ed502b2
+size 4111380520

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45282377e08ffaf9b4a94f5e29114d1eddb967b951259bfde1c398fcc443a81c
+size 4111431009

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}