Upload folder using huggingface_hub

config.json

@@ -1,32 +1,26 @@
 {
-  "_name_or_path": "./gemma-2-9b-it-gsm_sample_2500_nsk_ml512/m-iter-2_zq_raw",
+  "_name_or_path": "./gemma-1.1-7b-it-math_sample_2500_nsk_ml512/m-iter-2_zq_raw",
   "architectures": [
-    "Gemma2ForCausalLM"
+    "GemmaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
-  "cache_implementation": "hybrid",
   "eos_token_id": 1,
-  "final_logit_softcapping": 30.0,
   "head_dim": 256,
   "hidden_act": "gelu_pytorch_tanh",
   "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3584,
+  "hidden_size": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
+  "intermediate_size": 24576,
   "max_position_embeddings": 8192,
-  "model_type": "gemma2",
+  "model_type": "gemma",
   "num_attention_heads": 16,
-  "num_hidden_layers": 42,
-  "num_key_value_heads": 8,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
   "use_cache": false,

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 2,
-  "cache_implementation": "hybrid",
   "eos_token_id": 1,
   "pad_token_id": 0,
   "transformers_version": "4.45.2"

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea2eadc90e2c75a7f72c1921894f4aab7642faee5cf457ffb6b9794f89ebf3a
-size 4903351912
+oid sha256:b5bdc61f376f0d3ec30ba5ed48fa7d4709aaaad5c9a94feea98f7a98fd03c5a4
+size 4995496656

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a119f44f7e4bbe03a822e43d552934c5b4a9dd334ceb291d478c90c72a5af7a4
-size 4947570872
+oid sha256:5c00ae6d900ac226e4df8e0c7cc54db57f8f6978710b8d25154a314205b25467
+size 4982953168

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb421eaa6113dad07b72f51f90be6be11d52c70441ab296f858e31632542101a
-size 4962221464
+oid sha256:5cfc27b34b9a7c66db52f10271bd2254b95d2bb8701e1e6615cd5eadb87247d8
+size 4982953200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec2f92a575c0213a86b2e6c882c095476394d4dc86439e00d21b5d636fead9b
-size 3670322200
+oid sha256:f8b69ab7f233b065da642d8c706184727bef182ece22df8f758d470ffa9bc4ec
+size 2113988336

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 18483411968
+    "total_size": 17075361792
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
@@ -9,8 +9,6 @@
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
@@ -20,8 +18,6 @@
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
@@ -31,8 +27,6 @@
     "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -42,8 +36,6 @@
     "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -53,8 +45,6 @@
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -64,8 +54,6 @@
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -75,74 +63,60 @@
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
@@ -152,19 +126,15 @@
     "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.pre_feedforward_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",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -174,8 +144,6 @@
     "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -185,272 +153,96 @@
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "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-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-00003-of-00004.safetensors",
-    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.pre_feedforward_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",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -460,8 +252,6 @@
     "model.layers.9.mlp.gate_proj.weight": "model-00002-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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.pre_feedforward_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",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
-size 34362873
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041

tokenizer_config.json

@@ -1737,262 +1737,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "255968": {
-      "content": "[toxicity=0]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255969": {
-      "content": "\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255970": {
-      "content": "\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255971": {
-      "content": "\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255972": {
-      "content": "\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255973": {
-      "content": "\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255974": {
-      "content": "\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255975": {
-      "content": "\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255976": {
-      "content": "\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255977": {
-      "content": "\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255978": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255979": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255980": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255981": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255982": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255983": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255984": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255985": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255986": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255987": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255988": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255989": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255990": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255991": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255992": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255993": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255994": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255995": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255996": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255997": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255998": {
-      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "255999": {
-      "content": "<unused99>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "additional_special_tokens": [