model and tokenizer first upload

config.json

@@ -0,0 +1 @@
+{"d_model": 1024, "n_layer": 48, "vocab_size": 32000, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2093be9f3a7a991c62be35020295c46d099c3b83f85fe69bb0871f04abf32706
+size 709121042

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "added_tokens_decoder": {
+    "31996": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '###system:\n'+message['content']+'\n' }}{% endif %}{% if message['role'] == 'user' %}{{ '###User:\n' }}{{ message['content']}}{{ '\n###Assistant:\n' }}{% endif %}{% if message['role'] == 'assistant' %}{{ message['content']+eos_token}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "do_clean_text": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXJapaneseTokenizer",
+  "unk_token": "<|endoftext|>"
+}