Upload Gemma2ForCausalLM

config.json

@@ -1,28 +1,34 @@
 {
-  "_name_or_path": "google/gemma-1.1-7b-it",
+  "_name_or_path": "google/gemma-2-9b-it",
   "architectures": [
-    "GemmaForCausalLM"
+    "Gemma2ForCausalLM"
   ],
   "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": 3072,
+  "hidden_size": 3584,
   "initializer_range": 0.02,
-  "intermediate_size": 24576,
+  "intermediate_size": 14336,
   "max_position_embeddings": 8192,
-  "model_type": "gemma",
+  "model_type": "gemma2",
   "num_attention_heads": 16,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
   "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": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.42.4",
   "use_cache": true,
   "vocab_size": 256000
 }

generation_config.json

@@ -1,7 +1,8 @@
 {
   "_from_model_config": true,
   "bos_token_id": 2,
+  "cache_implementation": "hybrid",
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.42.4"
 }

model-00001-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a1c887ed19b1d841bd918994a289d39840d7c7c3d6af80653642087b7e580b
-size 4756367064
+oid sha256:f7d1ba9763552d40e273dbc1c7673800ba78bae4adf0034484f835d8f15fabf0
+size 4844480456

model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b40a7cb62ab11cfd82a62fc3e29de82d1ed13bf36da6205961375edef7ee65
-size 4731277472
+oid sha256:b468bd09fd8e5bd4abf8f623aef2efafbee88b1a38573c554f08d24e90cf0612
+size 4962213464

model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bce9c2b4978febe13345822b40be164fd5a87167232b43adf492c1d36391d4f
-size 4932629344
+oid sha256:fd6c62bc5d7a2dbe0f0a8e73c8fe12080c572499c38f7a0b484a8e6eb3e8a8c6
+size 4962271312

model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094e03bb9a69b8adf237d4618547d002076687a12be97aa3fb89ff8830007f5e
-size 4731277512
+oid sha256:b6581098048a785dc31fa16da9fba81a2c325fca978bdc995ff9151b287857aa
+size 4932853744

model-00005-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26569553bc0974d9a089f0af1aeab403d1e00091e259ba80b60d951520967e9
-size 4731277512
+oid sha256:de4ec3edd8d79e9df1328cc3913e4fdddaf43ecaef975343b0f6d9fc71f37718
+size 4962213528

model-00006-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85eabf13c28f2a990b9b0e1445ba8034b62953931af4f63be25b306e571ff84
-size 4932629384
+oid sha256:a339f964465cfb242f4c61715d5a5f6bffcff5038b2f1db9f813a5bf882e3477
+size 4962213528

model-00007-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24473f99490068127c2a16e0d03cdcd39f26317530110672c89707ee819d78f
-size 4731277512
+oid sha256:7cd602068ffdfb26e9916619f2fc89585f724d27cecf0274be553b9048b31cd0
+size 4962271328

model-00008-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82234b31b6e3d63a9d912b036fa30c77550be062e839f4bc430264397681051f
-size 604017208
+oid sha256:b86dee74efc98acd9d5b9828aa400ab7e2b197b8f827d3171804b54052deee32
+size 2378360680

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 34150723584
+    "total_size": 36966823936
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
@@ -9,6 +9,8 @@
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00008.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
@@ -18,231 +20,437 @@
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00008-of-00008.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
@@ -252,6 +460,8 @@
     "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",