Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/workspace/toupload",
+  "_name_or_path": "/workspace/weeeeee.1",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -14,7 +14,7 @@
   "max_position_embeddings": 32768,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 33,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
@@ -22,7 +22,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.36.2",
-  "use_cache": true,
+  "transformers_version": "4.37.2",
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,6 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.37.2",
   "use_cache": false
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2040625673494ce165d11e609379da33b6d7475c2f76eb16e5ffc5a3bf7ae3d4
+oid sha256:2e706e37a2f591daf1edfd5c19292ae308e03ccf1b6ff6762952d9cb043a98c3
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f4eb4e925aca6629287184da8049fdec2cc3138aaf5d28206f7ab7c09dc94e
+oid sha256:5bfbd32f09b70eb83179885d37902ba9b927309127b3151584d47eef1b078a6d
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48d2e9efd7770deec1b86fcff990a5b90365af562b64001882a0a75f253e2eb
-size 4540516344
+oid sha256:bfaa98d1465405a58ab8b473bfb33603981f0c5af990fb33004d9e82bf076f4f
+size 4976741400

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 14919688192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -239,6 +239,15 @@
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",