初始化项目，由ModelHub XC社区提供模型

Model: AlexWortega/instruct_rugptMedium
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,113 @@
+---
+datasets:
+- IlyaGusev/habr
+- Den4ikAI/russian_instructions
+- wiki_qa
+inference:
+  parameters:
+    min_length: 20
+    max_new_tokens: 100
+    top_k: 50
+    top_p: 0.9 
+    early_stopping: True
+    no_repeat_ngram_size: 2
+    use_cache: True
+    repetition_penalty: 1.5 
+    length_penalty: 0.8
+    num_beams: 4
+        
+license: apache-2.0
+language:
+- ru
+pipeline_tag: text-generation
+widget:
+- text: "Может ли встретиться пингвин и белый медведь?"
+  example_title: Question Answering
+- text: "Как зарабатывать много денег обучая модели?"
+  example_title: Open domain Knoweledge
+- text: "Напиши код который выведет Привет Мир"
+  example_title: Scientific knowledge
+library_name: transformers
+tags:
+- finance
+- code
+---
+
+<h1 style="font-size: 42px">Instructions ruGPT Medium v0.11_75к_a<h1/>
+
+
+
+# Model Summary
+
+> Это ruGPTMedium дообученная в инструктивно-флановом сетапе, она более ли менее ZSшотиться и FSшотиться и работает лучше чем XGLM1.7b, mgpt на русском языке
+
+
+# Quick Start
+
+```python
+from transformers import pipeline
+#в душе не ебу будет ли норм работать, ставлю жопу автора хф что токенайзер мисматчнет с моделью, вообще грузите по нормальному
+pipe = pipeline(model='AlexWortega/instruct_rugptMedium')
+pipe('''Как собрать питон код?''')
+```
+or
+```python
+from transformers import GPT2TokenizerFast,GPT2LMHeadModel
+tokenizer = GPT2TokenizerFast.from_pretrained("AlexWortega/instruct_rugptMedium")
+special_tokens_dict = {'additional_special_tokens': ['<code>', '</code>', '<instructionS>', '<instructionE>', '<next>']}
+
+tokenizer.add_special_tokens(special_tokens_dict)
+device = 'cuda:1'
+model = GPT2LMHeadModel.from_pretrained("AlexWortega/instruct_rugptMedium")
+model.to(device)
+
+model.resize_token_embeddings(len(tokenizer))
+```
+обратите внимание, что лучшие параметры для генерации 
+```
+gen_kwargs = {
+        "min_length": 20,
+        "max_new_tokens": 100,
+        "top_k": 50,
+        "top_p": 0.9,
+        "do_sample": True,  
+        "early_stopping": True,
+        "no_repeat_ngram_size": 2,
+        "eos_token_id": tokenizer.eos_token_id,
+        "pad_token_id": tokenizer.eos_token_id,
+        "use_cache": True,
+        "repetition_penalty": 1.5,  
+        "length_penalty": 0.8,  
+        "num_beams": 4,
+        "num_return_sequences": k
+    }
+```  
+# License
+
+The weights of Instructions ruGPT Small v0.1a are licensed under version 2.0 of the Apache License.
+
+
+
+## Hyperparameters
+
+I used Novograd with a learning rate of 2e-5 and global batch size of 6 (3 for each data parallel worker).
+I use both data parallelism and pipeline parallelism to conduct training.
+During training, we truncate the input sequence to 1024 tokens, and for input sequence that contains less than 1024 tokens, we concatenate multiple sequences into one long sequence to improve the data efficiency.
+
+
+
+# References
+
+#Metrics
+
+SOON
+
+## BibTeX entry and citation info
+
+```bibtex
+@article{
+  title={GPT2xl is underrated task solver},
+  author={Nickolich Aleksandr, 5Q, datascience, Ilya Gusev, Alex Kukushkin, Karina Romanova, Arseniy Shahmatov, Maksim Gersimenko},
+  year={2023}
+}
+```

added_tokens.json

@@ -0,0 +1,8 @@
+{
+  "</code>": 50259,
+  "<code>": 50258,
+  "<instructionE>": 50261,
+  "<instructionS>": 50260,
+  "<next>": 50262,
+  "<|endoftext|>": 50257
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "ckpts11/sft_0_65000/",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "n_special": 0,
+  "output_past": true,
+  "predict_special_tokens": true,
+  "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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50263
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e11331edf881259e1ae8bdedb8ba4a5b6cf33f9b7d03813e82cb48a411df961
+size 1524280989

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "<code>",
+    "</code>",
+    "<instructionS>",
+    "<instructionE>",
+    "<next>"
+  ],
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}