Upload tiny models for GPTNeoXJapaneseForCausalLM

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "GPTNeoXJapaneseForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 31996,
+  "eos_token_id": 31999,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_multiple_size": 4,
+  "is_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 512,
+  "model_type": "gpt_neox_japanese",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 5,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 32000,
+  "weight_tying": true
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 31996,
+  "eos_token_id": 31999,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37da46a676123a90378a498f8030a629d20d6127822e4a015aa903569800feb
+size 4360708

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_clean_text": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPTNeoXJapaneseTokenizer",
+  "unk_token": "<|endoftext|>"
+}