Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Brownwang0426/Llama-3-Taiwan-8B-Instruct-to-1B",
+  "_name_or_path": "yentinglin/Llama-3-Taiwan-8B-Instruct-rc2",
   "architectures": [
     "LlamaForCausalLM"
   ],

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2543a6eac6fceb73d9502c00e3ad106a34a1c01f3a7626012bd3ea91ac8687e
-size 4953543640
+oid sha256:9f6e706b9e91d5614b3b8d1a6eb9e1a6dc4890e62fdbbed613ed814725c5a3af
+size 4953543368

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90083e6c4ae097927802453b3d79e6a68c86084c3d0a9e39690312ae71cad16
-size 3141617056
+oid sha256:c4e05a23c1a1166bcf547324e8e500acee1eaff5949fc390f3bf15b16c1d549c
+size 2806072080

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8095154176
+    "total_size": 7759609856
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -26,10 +26,6 @@
     "model.layers.0.self_attn.custom_attn.W_v_1.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.custom_attn.W_v_2.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.custom_attn.W_v_final.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
@@ -38,23 +34,19 @@
     "model.layers.1.self_attn.custom_attn.W_k_0.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_k_1.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_k_2.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.custom_attn.W_k_final.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.custom_attn.W_k_final.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_o_0.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_o_1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.custom_attn.W_o_2.weight": "model-00002-of-00002.safetensors",
-    "model.layers.1.self_attn.custom_attn.W_o_final.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.custom_attn.W_o_2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.custom_attn.W_o_final.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_q_0.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_q_1.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_q_2.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.custom_attn.W_q_final.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.custom_attn.W_q_final.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_v_0.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_v_1.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.custom_attn.W_v_2.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.custom_attn.W_v_final.weight": "model-00002-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.custom_attn.W_v_final.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }