From 658edeb2a7a30aefd6abc109ba0fd73dee08ba3d Mon Sep 17 00:00:00 2001 From: kurumuz Date: Thu, 5 Aug 2021 17:56:49 +0000 Subject: [PATCH] upload 6B weights --- config.json | 49 +++++++++++++++++++++++++++++++++++++++++++++++ pytorch_model.bin | 3 +++ 2 files changed, 52 insertions(+) create mode 100644 config.json create mode 100644 pytorch_model.bin diff --git a/config.json b/config.json new file mode 100644 index 0000000..7b25bc7 --- /dev/null +++ b/config.json @@ -0,0 +1,49 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPTJForCausalLM" + ], + "attention_dropout": 0, + "attention_layers": ["global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global"], + "attention_types": [ + [ + [ + "global" + ], + 28 + ] + ], + "bos_token_id": 50256, + "embed_dropout": 0, + "eos_token_id": 50256, + "gradient_checkpointing": false, + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": null, + "jax": true, + "layer_norm_epsilon": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gptj", + "num_heads": 16, + "num_layers": 28, + "resid_dropout": 0, + "rotary": true, + "rotary_dim": 64, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "transformers_version": "4.10.0.dev0", + "use_cache": true, + "vocab_size": 50400, + "window_size": 256, + "tokenizer_class": "GPT2Tokenizer", + "task_specific_params": { + "text-generation": { + "do_sample": true, + "temperature": 1.0, + "max_length": 50 + } + } + } \ No newline at end of file diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..09b5730 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2983ccc0a206013798f2e50a6b8fae0579d5ce18ee25d4d6c6221db0f3e875 +size 12571637995