add model

config.json

@@ -0,0 +1,26 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "XGLMForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_heads": 16,
+  "bos_token_id": 0,
+  "d_model": 2048,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 16384,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "xglm",
+  "num_layers": 48,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 256008
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e3b1f47d4ec3ccb5d1ee667ad6ce0f73af3ca689fb93b9bfdd8ab617f64ff1
+size 10153902621

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
+size 4920706

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "additional_special_tokens": ["<madeupword0>", "<madeupword1>", "<madeupword2>", "<madeupword3>", "<madeupword4>", "<madeupword5>", "<madeupword6>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json", "additional_special_tokens": ["<madeupword0>", "<madeupword1>", "<madeupword2>", "<madeupword3>", "<madeupword4>", "<madeupword5>", "<madeupword6>"], "name_or_path": "hf_models/xglm-564M", "tokenizer_class": "XGLMTokenizer"}