Add 810k based KoAlpaca v1.0 finetuned model

.gitignore

@@ -0,0 +1 @@
+.ipynb_checkpoints/

config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "beomi/KoAlpaca-KoRWKV-1.5B",
+  "architectures": [
+    "RwkvForCausalLM"
+  ],
+  "attention_hidden_size": 2048,
+  "bos_token_id": 0,
+  "context_length": 16384,
+  "eos_token_id": 0,
+  "hidden_size": 2048,
+  "intermediate_size": 8192,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "rwkv",
+  "num_hidden_layers": 24,
+  "rescale_every": 6,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.30.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d6748a511fb2308750e4116cb6c0171e31c9a6e816962a3f3d5b9c9c5d55a6
+size 6088802697

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|sep|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<|sep|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}