Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/Training/TrainedModel3B/",
+  "_name_or_path": "/Training/SN9TrainedModel3B/",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,14 +21,10 @@
   "num_attention_heads": 24,
   "num_hidden_layers": 24,
   "num_key_value_heads": 24,
-  "pop_states_at_layer": null,
   "pretraining_tp": 1,
-  "return_states_at_layer": null,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "start_at_layer": null,
-  "stash_states_at_layer": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4ace5d09552bc4d7df3dcc888d3eae58a1c052c980a56b375b1999fb9a7020
+oid sha256:eb2ac7b7d03d6915ea4f8e3905b83c22d35cff236f137e39b35757f16c006e4e
 size 4971811976

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59412f144c256b8d8f7f5d43a45e74b0a324ff182f2c3b637138e9d9348dbbbf
+oid sha256:75fd98b950f7538dd779a624b03dbd276b00302f7671d0be907dc3d09f21643b
 size 1828189840