Upload GPTNeoXForCausalLM

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "line-corporation/japanese-large-lm-3.6b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca765d73cabf1c78a4277a5882ad29fc271993f7ec33f01f047158032bfba1b7
+size 314572936