Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./Llama3_DiscoLM_German_8b_v0.1_experimental",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,7 +21,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0.dev0",
   "use_cache": true,
   "vocab_size": 128256

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aceb4571f7b37825911de0366036351c947e47cee450a0bcf04309f0da1af0b0
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd89e18901f923dfd1eaf67200fd1287314aea524047a5cdda539ffb78f473ae
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bbc563a8545ebbbdfd62554386aebc47832df8105e6bc1ee934e37c74d84f77
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21295d56c87bbcea11a95594e4dc8c92e8eecdd7acfcaf765ee3ff7daad492d9
+size 1168138808

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 32121044992
+    "total_size": 16060522496
   },
   "weight_map": {
-    "lm_head.weight": "model-00007-of-00007.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.norm.weight": "model-00007-of-00007.safetensors"
+    "lm_head.weight": "model-00004-of-00004.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-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.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-00002-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-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.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-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.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.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.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-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.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-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-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"
   }
 }

special_tokens_map.json

@@ -1,20 +1,20 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -5,7 +5,7 @@
   "added_tokens": [
     {
       "id": 128000,
-      "content": "<|im_start|>",
+      "content": "<|begin_of_text|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -14,7 +14,7 @@
     },
     {
       "id": 128001,
-      "content": "<|im_end|>",
+      "content": "<|end_of_text|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,7 @@
     },
     {
       "id": 128002,
-      "content": "<s>",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -32,7 +32,7 @@
     },
     {
       "id": 128003,
-      "content": "</s>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2329,58 +2329,10 @@
     ]
   },
   "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
-      {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
-      }
-    ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          128002
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": false,
+    "use_regex": true
   },
   "decoder": {
     "type": "ByteLevel",

tokenizer_config.json

@@ -3,7 +3,7 @@
   "add_eos_token": false,
   "added_tokens_decoder": {
     "128000": {
-      "content": "<|im_start|>",
+      "content": "<|begin_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -11,7 +11,7 @@
       "special": true
     },
     "128001": {
-      "content": "<|im_end|>",
+      "content": "<|end_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -19,7 +19,7 @@
       "special": true
     },
     "128002": {
-      "content": "<s>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -27,7 +27,7 @@
       "special": true
     },
     "128003": {
-      "content": "</s>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2051,16 +2051,18 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "<|begin_of_text|>",
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "legacy": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<|end_of_text|>",
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }