Upload folder using huggingface_hub

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "LLARA-beir",
   "architectures": [
-    "LlamaModel"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -22,7 +22,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.38.1",
   "use_cache": false,
   "vocab_size": 32016
 }

generation_config.json

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.33.0"
+  "transformers_version": "4.38.1"
 }

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae2c67ccd1d1a48aa4e2f674df64e056402759085bf98f9ba4806b820bfcee7
-size 4840658256
+oid sha256:01dd7ea5dfa7418b6f2d6a29c50d7a632a74459e5445f6d13d04b22f23201f13
+size 4840658560

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e9084662c6c8f6abcc800098b786fe4682992c06305e2b03f94e3f6c20a459
-size 4857206528
+oid sha256:bde0b61c7e53a84ddc7432a2049fb125191da2a7d5dbae7fe4a592f35e2224fc
+size 4857206856

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913d76c903383ba25f39bed9b1d2007145aa91443de5ca07dd84cf7c8411bd08
-size 4857206576
+oid sha256:75c9c8c1a7ffdc359e7be1ec0e40c7598d2a2167c1ea1380ad67b5409c80c4f2
+size 4857206904

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6987077d4cd21c5068c293d28698a86343327e875bc88c1b469395f2492cb8
-size 4857206576
+oid sha256:b99f7143e6bb96b6d56fbda293f97e4aa7554a13691949e5aa0d3ccdd422029f
+size 4857206904

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75df8fada486a22b56774933776ac0516fe196b186f52a2ec1f28e7afd9648ce
-size 4857206576
+oid sha256:728bfd285dd8bf48458715de351982e1fa9449a8cf8111f2e9da05e567e3c346
+size 4857206904

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23c957c4ec4202d670d1458ba700856c8a103fd5214ce64cad438907d9fd51a
-size 2160183864
+oid sha256:d5034cc2eafecc0c004dad0880a7e7d75a61bd8ecdf2b1e4bfdc6bd1b8f9e8b7
+size 2684734256

model.safetensors.index.json

@@ -1,297 +1,298 @@
 {
   "metadata": {
-    "total_size": 26429636608
+    "total_size": 26954186752
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "norm.weight": "model-00006-of-00006.safetensors"
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
   }
 }

special_tokens_map.json

@@ -1,117 +1,21 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<s9>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s12>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s7>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s14>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s3>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s6>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s15>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s5>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s1>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s10>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s13>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s11>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s4>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s8>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s16>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<s9>",
+    "<s12>",
+    "<s7>",
+    "<s14>",
+    "<s3>",
+    "<s6>",
+    "<s15>",
+    "<s5>",
+    "<s1>",
+    "<s10>",
+    "<s13>",
+    "<s2>",
+    "<s11>",
+    "<s4>",
+    "<s8>",
+    "<s16>"
   ],
   "bos_token": {
     "content": "<s>",
@@ -127,7 +31,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<unk>",
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -173,44 +174,16 @@
     "<s8>",
     "<s16>"
   ],
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<unk>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "unk_token": "<unk>",
   "use_default_system_prompt": true
 }