Upload CompressedLlamaForCausalLM

config.json

@@ -19,8 +19,10 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "share_layers": "none",
   "tie_word_embeddings": false,
+  "tied_layers": {
+    "1": 0
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cde221462593019af025faf5cce19f0bcf432f6106d8d4f6193ef65dde77dec
-size 4993264136
+oid sha256:410627979de4319c4623cd5dbc988483c182d26e893f6d230a6ef6134bd482a7
+size 4923632128

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da989a50e26cc2e59c9c546b439ea6d3cedbf2090068f1159b61bfde743970ba
-size 4997386488
+oid sha256:2d81c6fa49d323e616f26b3a824a2f73049c2596008583b13a3d7a38115647a4
+size 4956426376

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e75f2f2edceb7bee4131d7e189af5f09aaa91d3f9b95b62b53811fb671293b
-size 3715271008
+oid sha256:2c138227dedead48e31613d734e633baf4096b895901d045ef51944dd19c2631
+size 3494086776

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13705894400
+    "total_size": 13374118400
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -15,9 +15,6 @@
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -106,8 +103,8 @@
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -232,11 +229,11 @@
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.norm.weight": "model-00003-of-00003.safetensors"