gpt-j-base-v1-lr6e-4-batch8-rev1

.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
+flax_model.msgpack filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "heegyu/kogpt-j-base",
   "activation_function": "gelu_new",
   "architectures": [
     "GPTJForCausalLM"
@@ -7,8 +8,6 @@
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
   "eos_token_id": 2,
-  "pad_token_id": 0,
-  "unk_token_id": 5,
   "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
@@ -18,6 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "pad_token_id": 0,
   "resid_pdrop": 0.0,
   "rotary_dim": 16,
   "scale_attn_weights": true,
@@ -28,7 +28,8 @@
   "summary_use_proj": true,
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
-  "transformers_version": "4.24.0",
+  "transformers_version": "4.25.1",
+  "unk_token_id": 5,
   "use_cache": true,
   "vocab_size": 51200
-}
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8b46abacb8ace04f4c0bdecff4272906163325784aaf8ae1de9be293949080
+size 654785094

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ ì
 Ġ ë
 ì Ŀ

tokenizer_config.json

@@ -18,7 +18,8 @@
     "single_word": false
   },
   "errors": "replace",
-  "name_or_path": "models/tokenizer-51k",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "heegyu/kogpt-j-base",
   "pad_token": null,
   "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",