Upload LlamaForCausalLM

config.json

@@ -1,36 +1,39 @@
 {
   "architectures": [
-    "Qwen3ForCausalLM"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 2560,
+  "hidden_size": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 9728,
-  "max_position_embeddings": 40960,
-  "max_window_layers": 36,
-  "model_type": "qwen3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
   "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "sliding_window": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936,
-  "rope_scaling": {
-      "rope_type": "yarn",
-      "factor": 4.0,
-      "original_max_position_embeddings": 32768
-  }
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "vocab_size": 128256
 }
-

generation_config.json

@@ -1,13 +1,11 @@
 {
-  "bos_token_id": 151643,
-  "do_sample": true,
+  "_from_model_config": true,
+  "bos_token_id": 128000,
   "eos_token_id": [
-    151645,
-    151643
+    128001,
+    128008,
+    128009
   ],
-  "pad_token_id": 151643,
-  "temperature": 0.6,
-  "top_k": 20,
-  "top_p": 0.95,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.52.4",
+  "use_cache": false
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0ad67298a3e57b2f3340047e29402a753b863a799225f56308bfd2c64eebc9
-size 4967215360
+oid sha256:0787cfc9a4b2b19a1589efa77ec34468ae03505a3188294bbdcfce386bd50026
+size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c94860e18e1e19f3afffc6d6c8aeac94fc4b2a27a156e26eab4df1e5d7cf07
-size 3077766632
+oid sha256:4e4f296f94775ed459b65ab2b7cb1fb741822f97465f7479a1b1ddf7b21641f4
+size 1459729952

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8044936192
+    "total_size": 6425499648
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -9,10 +9,8 @@
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_norm.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_norm.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-00001-of-00002.safetensors",
@@ -20,10 +18,8 @@
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_norm.weight": "model-00001-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_norm.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.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -31,10 +27,8 @@
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -42,10 +36,8 @@
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -53,10 +45,8 @@
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -64,10 +54,8 @@
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -75,10 +63,8 @@
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -86,10 +72,8 @@
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -97,10 +81,8 @@
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -108,10 +90,8 @@
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -119,10 +99,8 @@
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -130,10 +108,8 @@
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -141,10 +117,8 @@
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -152,10 +126,8 @@
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -163,10 +135,8 @@
     "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -174,10 +144,8 @@
     "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -185,10 +153,8 @@
     "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -196,10 +162,8 @@
     "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -207,10 +171,8 @@
     "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -218,10 +180,8 @@
     "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -229,120 +189,26 @@
     "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -350,10 +216,8 @@
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -361,10 +225,8 @@
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -372,10 +234,8 @@
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -383,10 +243,8 @@
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -394,10 +252,8 @@
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"