Upload 6 files

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "/cache/stage1_trained_models_300M/iter_0500000_hf/",
+  "activation_function": "gelu",
+  "architectures": [
+    "PanguAlphaModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": 4096,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "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,
+  "tokenizer_class": "_JIEBATokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.19.0",
+  "use_cache": true,
+  "vocab_size": 64007
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a7b69396650c63597e37123737ed0ce13f08c28c2114a98e604cbef7a08bb5
+size 791629068

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<eod>", "<eot>", "<pad>", "<java>", "<python>", "<go>", "<php>", "<javascript>", "<ruby>", "<en>", "<cn>", "<comments>", "<NEW_LINE>", "<INDENT>", "<DEDENT>", "<mask>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": false, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": [], "sp_model_kwargs": {}, "tokenizer_class": "PanguAlphaTokenizer"}

vocab.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe6b97eda224f26b4cb815bb74f4d8b58af5464945ad174e9001aaa721ca4df
+size 723771