Upload 7 files

README.md

@@ -0,0 +1,14 @@
+---
+language:
+- ru
+tags:
+- PyTorch
+- Transformers
+thumbnail: "https://github.com/sberbank-ai/ru-gpts"
+---
+
+# rugpt3large\_based\_on\_gpt2
+Model was trained with sequence length 1024 using transformers lib by [SberDevices](https://sberdevices.ru/) team on 80B tokens for 3 epochs. After that model was finetuned 1 epoch with sequence length 2048. 
+
+Total training time was around 14 days on 128 GPUs for 1024 context and few days on 16 GPUs for 2048 context.  
+Final perplexity on test set is `13.6`.

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": 1536,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "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
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f93f7c9af006b72f3e61038597127ff41cf2f5752b35db64fdca1a7b1242ad
+size 3041209758

gitattributes.txt

@@ -0,0 +1,9 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2ca7dbc12badb0a610df6f853168d6d9446a3b51e13e8af9186220eacc05cb
+size 3141928084