Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/lunarsylph/_code_/neuralpantheon/output-model-directory",
+  "_name_or_path": "/home/lunarsylph/_code_/neuralpantheon/__PEFT__/output",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -24,5 +24,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
   "use_cache": false,
-  "vocab_size": 128256
+  "vocab_size": 100290
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
+  "do_sample": true,
   "eos_token_id": 128001,
-  "transformers_version": "4.40.0",
-  "use_cache": false
+  "transformers_version": "4.40.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d1e235a8553bc7f486595046c10b30372f7eeeede7a73c49dc169ff97be325
-size 4976698672
+oid sha256:2fd41cc3c98e42778cc2d30acf1b5770f495ddb6944c38ee0be464077db0297a
+size 4948928368

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a387b1252e856e997b569014e198e342daed4a2690964faa14877360858c88
-size 4999802720
+oid sha256:cc70cac42a1a20102a8681347bff66d6b2a6ab0f0ecdfdba82cc2d0d44cfaeff
+size 4915916168

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d5b1298d13884312eea71d47a3841ee8335058dc2c39a559eb9688bbf23879
-size 4915916176
+oid sha256:30cb6a3c3e5aad28615fd291b2ea79a67ea9922db412b0dca834669328978abd
+size 4915941072

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abc53444813a8946947f9d3db0c5db49b33b074d2f82d1aa41e6efff2d13d0f
-size 1168138808
+oid sha256:b75672657c68183f4f1cde84a7aa352e98bb7db287e900a064e5621a6e17a384
+size 821575808

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16060522496
+    "total_size": 15602327552
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",
@@ -125,7 +125,7 @@
     "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
@@ -230,11 +230,11 @@
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -286,13 +286,13 @@
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.norm.weight": "model-00004-of-00004.safetensors"
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
   }
 }