Upload GPTNeoXForCausalLM

config.json

@@ -6,8 +6,8 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classifier_dropout": 0.1,
-  "dtype": "bfloat16",
-  "eos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
   "hidden_size": 8,
@@ -18,6 +18,7 @@
   "model_type": "gpt_neox",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
   "partial_rotary_factor": 0.25,
   "rope_scaling": null,
   "rope_theta": 10000,
@@ -27,5 +28,5 @@
   "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "use_parallel_residual": true,
-  "vocab_size": 50304
+  "vocab_size": 50277
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "eos_token_id": 0,
+  "eos_token_id": 2,
   "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44442826f19b5f5637fb789b0bc27f92dbaf5cba987b3e9fc72662a2f2bc068
-size 1616272
+oid sha256:9a6bdc7b4adcc5b815314292e533d8b7df057530b0ab2d185925f6a2a92dc5de
+size 3227768