Upload tiny models for XGLMForCausalLM

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "tiny_models/xglm/XGLMForCausalLM",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "architectures": [
+    "XGLMForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_heads": 4,
+  "bos_token_id": 0,
+  "d_model": 32,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 37,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "xglm",
+  "num_layers": 5,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 256008
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15d53bab6a071c8268f776892a5d02a1d4c9b9ea45908e9f6bc0b63f7d569d6
+size 32930730

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 +1,17 @@
+{
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af3e88701a2f9ed84ee9b5d2bad86169237c8608cb495be7d8632730d83f711
+size 65836840

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c48025c56c78c2e1805007e6e068bf61ceedce91484eae064957cb865dcfec2
+size 17225862

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json",
+  "tokenizer_class": "XGLMTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}