初始化项目，由ModelHub XC社区提供模型

Model: 4eJIoBek/ruGPT3_small_nujdiki_stage1
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
+*.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
+rugpt3_small_nujdiki_stage1-f16.gguf filter=lfs diff=lfs merge=lfs -text
+rugpt3_small_nujdiki_stage1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,15 @@
+---
+license: wtfpl
+---
+это файнтюн sberai ruGPT3 small (125 млн параметров) на всех оригинальных нуждиках (2 часа транскрибированные через openai whisper medium). размер блока при файнтюне 1024, 25 эпох. все скрипты по инференсу модели тут https://github.com/ai-forever/ru-gpts, через transformers вполне себе работает на 4 гб видеопамяти, на 2 думаю тоже заработает.
+
+-как запустить через transformers?
+запускаем строки ниже в jupyterе
+
+from transformers import pipeline, set_seed
+
+set_seed(32)
+generator = pipeline('text-generation', model="4eJIoBek/ruGPT3_small_nujdiki_fithah", do_sample=True, max_length=350)
+generator("Александр Сергеевич Пушкин известен также благодаря своим сказкам, которые включают в себя: ")
+
+и всё работает и вообще нихуёво

config.json

@@ -0,0 +1,27 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "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,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "vocab_size": 50257
+}

dataset.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01179611e19c8b2f2414e311a466c03cdf7f9cfa88dc09cbf14b858d239ab2a9
+size 95136

eval_results.txt

@@ -0,0 +1 @@
+perplexity = tensor(1.1213)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2ee43ad2d67a59f1a389dcb894bf3fc97ea2838464cd29988747ad8990f612
+size 551254064

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e4f9983870460d0264dd74918428e99146f0bcdc660857093e9346cd55f155
+size 551301024

rugpt3_small_nujdiki_stage1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2575475819fb509965fbc1040ee2b8fd78248df56c346d3e6fb5d8b4b1b2fb79
+size 141433952

rugpt3_small_nujdiki_stage1-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b15db37676fb7227a3dc45f6c3ceaaca11139dd975ec45e5796e9d895bac0e
+size 257245216

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"special_tokens_map_file": null, "full_tokenizer_file": null}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3bc8f8c4130325c4fc784a1bf92e03fa1d63de60dbc1deb35261909ba9a292
+size 1519