Upload GemmaForCausalLM

README.md

@@ -1,9 +1,9 @@
 ---
+license: other
 library_name: transformers
 datasets:
 - HuggingFaceH4/ultrafeedback_binarized
 base_model: tcapelle/gemma-7b-zephyr-sft
-license: other
 license_name: gemma-terms-of-use
 license_link: https://ai.google.dev/gemma/terms
 ---

config.json

@@ -21,7 +21,7 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.38.1",
   "use_cache": true,
   "vocab_size": 256000

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bee3d726956db090ea032159b5e351d7552b4bacd98279b486272b65bc50ee7
+size 4995496656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0162ff8c54b41a00d1812d4fe62264f07019b8b81824ca118eb10dc74b5de927
+size 4982953168

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c361b22345dcb48ff7a0d16c2caa116066f66f5fb5a60d7b2b1fa60d852896ac
+size 4982953200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00baf5776f3a7c3078ff46e1a4aa483cc3da0576476c8acb10b602646647402a
+size 2113988336

model.safetensors.index.json

@@ -1,261 +1,261 @@
 {
   "metadata": {
-    "total_size": 34150723584
+    "total_size": 17075361792
   },
   "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
-    "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.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",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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",
-    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "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.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",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.norm.weight": "model-00008-of-00008.safetensors"
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "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.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",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "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.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",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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-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-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.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",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-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.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.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",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "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.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",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "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.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-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-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.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.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.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.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.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-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-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.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.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",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }