Upload model

config.json

@@ -1,35 +1,36 @@
 {
-  "_name_or_path": "a5",
+  "_name_or_path": "083224",
   "architectures": [
-    "Gemma2ForCausalLM"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "attn_logit_softcapping": 50.0,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
-  "eos_token_id": 1,
-  "final_logit_softcapping": 30.0,
-  "head_dim": 256,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3584,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma2",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 42,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 0,
-  "query_pre_attn_scalar": 224,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "sliding_window_size": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.3",
-  "use_cache": true,
-  "vocab_size": 256000
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "vocab_size": 128258
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.48.1",
+  "use_cache": false
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e95d5721dc87bf3ff0df0b6cb6876a2d255d83c19e27f4a0ebf1e4279dc9c5
+size 4976715056

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:588d38b90b65e2d475b49f0a360b87f75eb85a38908c0d2da82c414333f3971a
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b78055bbfd78bdc7b1fba1c6b1ca3c2921f85ceb4f8db265232f0bc0a598b04
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4817b03b2cc153a0c02e7142945660c9e6bc54d6d418db54cfcbaf97b6cf21a7
+size 1168155192

model.safetensors.index.json

@@ -1,474 +1,299 @@
 {
     "metadata": {
-        "mergekit_version": "0.0.4.4",
-        "total_size": 20318419968,
-        "timestamp": "1737130954.5248053"
+        "total_size": 16060555264,
+        "timestamp": "1737736996.221368"
     },
     "weight_map": {
-        "lm_head.weight": "model-00001-of-00005.safetensors",
-        "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
-        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.34.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "model.layers.34.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-        "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-        "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-        "model.norm.weight": "model-00005-of-00005.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

@@ -1,31 +1,24 @@
 {
   "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
+    "<|im_start|>",
+    "<|im_end|>"
   ],
   "bos_token": {
-    "content": "<bos>",
+    "content": "<|im_start|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<eos>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
-size 17518525
+oid sha256:510d12ec255f4cb0304aa5428d699c354c1a49696b427a2748a7b03bb7bbb575
+size 17210296

tokenizer_config.json

@@ -1,1757 +1,2084 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
+    "128000": {
+      "content": "<|begin_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<eos>",
+    "128001": {
+      "content": "<|end_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "<bos>",
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "<mask>",
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     },
-    "5": {
-      "content": "<2mass>",
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "6": {
-      "content": "[@BOS@]",
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "7": {
-      "content": "<unused0>",
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "8": {
-      "content": "<unused1>",
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "9": {
-      "content": "<unused2>",
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "10": {
-      "content": "<unused3>",
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "11": {
-      "content": "<unused4>",
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "12": {
-      "content": "<unused5>",
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "13": {
-      "content": "<unused6>",
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "14": {
-      "content": "<unused7>",
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "15": {
-      "content": "<unused8>",
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "16": {
-      "content": "<unused9>",
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "17": {
-      "content": "<unused10>",
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "18": {
-      "content": "<unused11>",
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "19": {
-      "content": "<unused12>",
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "20": {
-      "content": "<unused13>",
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "21": {
-      "content": "<unused14>",
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "22": {
-      "content": "<unused15>",
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "23": {
-      "content": "<unused16>",
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "24": {
-      "content": "<unused17>",
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "25": {
-      "content": "<unused18>",
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "26": {
-      "content": "<unused19>",
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "27": {
-      "content": "<unused20>",
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "28": {
-      "content": "<unused21>",
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "29": {
-      "content": "<unused22>",
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "30": {
-      "content": "<unused23>",
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "31": {
-      "content": "<unused24>",
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "32": {
-      "content": "<unused25>",
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "33": {
-      "content": "<unused26>",
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "34": {
-      "content": "<unused27>",
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "35": {
-      "content": "<unused28>",
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "36": {
-      "content": "<unused29>",
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "37": {
-      "content": "<unused30>",
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "38": {
-      "content": "<unused31>",
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "39": {
-      "content": "<unused32>",
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "40": {
-      "content": "<unused33>",
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "41": {
-      "content": "<unused34>",
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "42": {
-      "content": "<unused35>",
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "43": {
-      "content": "<unused36>",
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "44": {
-      "content": "<unused37>",
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "45": {
-      "content": "<unused38>",
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "46": {
-      "content": "<unused39>",
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "47": {
-      "content": "<unused40>",
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "48": {
-      "content": "<unused41>",
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "49": {
-      "content": "<unused42>",
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50": {
-      "content": "<unused43>",
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "51": {
-      "content": "<unused44>",
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "52": {
-      "content": "<unused45>",
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "53": {
-      "content": "<unused46>",
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "54": {
-      "content": "<unused47>",
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "55": {
-      "content": "<unused48>",
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "56": {
-      "content": "<unused49>",
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "57": {
-      "content": "<unused50>",
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "58": {
-      "content": "<unused51>",
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "59": {
-      "content": "<unused52>",
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "60": {
-      "content": "<unused53>",
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "61": {
-      "content": "<unused54>",
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "62": {
-      "content": "<unused55>",
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "63": {
-      "content": "<unused56>",
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "64": {
-      "content": "<unused57>",
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "65": {
-      "content": "<unused58>",
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "66": {
-      "content": "<unused59>",
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "67": {
-      "content": "<unused60>",
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "68": {
-      "content": "<unused61>",
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "69": {
-      "content": "<unused62>",
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "70": {
-      "content": "<unused63>",
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "71": {
-      "content": "<unused64>",
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "72": {
-      "content": "<unused65>",
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "73": {
-      "content": "<unused66>",
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "74": {
-      "content": "<unused67>",
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "75": {
-      "content": "<unused68>",
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "76": {
-      "content": "<unused69>",
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "77": {
-      "content": "<unused70>",
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "78": {
-      "content": "<unused71>",
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "79": {
-      "content": "<unused72>",
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "80": {
-      "content": "<unused73>",
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "81": {
-      "content": "<unused74>",
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "82": {
-      "content": "<unused75>",
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "83": {
-      "content": "<unused76>",
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "84": {
-      "content": "<unused77>",
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "85": {
-      "content": "<unused78>",
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "86": {
-      "content": "<unused79>",
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "87": {
-      "content": "<unused80>",
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "88": {
-      "content": "<unused81>",
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "89": {
-      "content": "<unused82>",
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "90": {
-      "content": "<unused83>",
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "91": {
-      "content": "<unused84>",
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "92": {
-      "content": "<unused85>",
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "93": {
-      "content": "<unused86>",
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "94": {
-      "content": "<unused87>",
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "95": {
-      "content": "<unused88>",
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "96": {
-      "content": "<unused89>",
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "97": {
-      "content": "<unused90>",
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "98": {
-      "content": "<unused91>",
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "99": {
-      "content": "<unused92>",
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "100": {
-      "content": "<unused93>",
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "101": {
-      "content": "<unused94>",
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "102": {
-      "content": "<unused95>",
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "103": {
-      "content": "<unused96>",
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "104": {
-      "content": "<unused97>",
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "105": {
-      "content": "<unused98>",
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "106": {
-      "content": "<start_of_turn>",
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "107": {
-      "content": "<end_of_turn>",
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "108": {
-      "content": "\n",
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "109": {
-      "content": "\n\n",
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "110": {
-      "content": "\n\n\n",
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "111": {
-      "content": "\n\n\n\n",
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "112": {
-      "content": "\n\n\n\n\n",
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "113": {
-      "content": "\n\n\n\n\n\n",
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "114": {
-      "content": "\n\n\n\n\n\n\n",
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "115": {
-      "content": "\n\n\n\n\n\n\n\n",
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "116": {
-      "content": "\n\n\n\n\n\n\n\n\n",
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "117": {
-      "content": "\n\n\n\n\n\n\n\n\n\n",
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "118": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "119": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "120": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "121": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "122": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "123": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "124": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "125": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "126": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "127": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "128": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "129": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "130": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "131": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "132": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "133": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "134": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "135": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "136": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "137": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "138": {
-      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "139": {
-      "content": "▁▁",
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "140": {
-      "content": "▁▁▁",
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "141": {
-      "content": "▁▁▁▁",
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "142": {
-      "content": "▁▁▁▁▁",
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "143": {
-      "content": "▁▁▁▁▁▁",
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "144": {
-      "content": "▁▁▁▁▁▁▁",
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "145": {
-      "content": "▁▁▁▁▁▁▁▁",
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "146": {
-      "content": "▁▁▁▁▁▁▁▁▁",
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "147": {
-      "content": "▁▁▁▁▁▁▁▁▁▁",
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "148": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "149": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "150": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "151": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     },
-    "152": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "153": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "154": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "155": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "156": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "157": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "158": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "159": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "160": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "161": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "162": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "163": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "164": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "165": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "166": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "167": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "168": {
-      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "169": {
-      "content": "<table>",
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "170": {
-      "content": "<caption>",
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "171": {
-      "content": "<thead>",
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "172": {
-      "content": "<tbody>",
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "173": {
-      "content": "<tfoot>",
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "174": {
-      "content": "<tr>",
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "175": {
-      "content": "<th>",
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "176": {
-      "content": "<td>",
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "177": {
-      "content": "</table>",
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "178": {
-      "content": "</caption>",
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "179": {
-      "content": "</thead>",
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "180": {
-      "content": "</tbody>",
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "181": {
-      "content": "</tfoot>",
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "182": {
-      "content": "</tr>",
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "183": {
-      "content": "</th>",
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "184": {
-      "content": "</td>",
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "185": {
-      "content": "<h1>",
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "186": {
-      "content": "<h2>",
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "187": {
-      "content": "<h3>",
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "188": {
-      "content": "<h4>",
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "189": {
-      "content": "<h5>",
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "190": {
-      "content": "<h6>",
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "191": {
-      "content": "<blockquote>",
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "192": {
-      "content": "</h1>",
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "193": {
-      "content": "</h2>",
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "194": {
-      "content": "</h3>",
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "195": {
-      "content": "</h4>",
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "196": {
-      "content": "</h5>",
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "197": {
-      "content": "</h6>",
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "198": {
-      "content": "</blockquote>",
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "199": {
-      "content": "<strong>",
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "200": {
-      "content": "<em>",
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "201": {
-      "content": "<b>",
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "202": {
-      "content": "<i>",
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "203": {
-      "content": "<u>",
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "204": {
-      "content": "<s>",
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "205": {
-      "content": "<sub>",
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "206": {
-      "content": "<sup>",
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "207": {
-      "content": "<code>",
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "208": {
-      "content": "</strong>",
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "209": {
-      "content": "</em>",
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "210": {
-      "content": "</b>",
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "211": {
-      "content": "</i>",
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "212": {
-      "content": "</u>",
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "213": {
-      "content": "</s>",
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "214": {
-      "content": "</sub>",
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "215": {
-      "content": "</sup>",
+    "128256": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "216": {
-      "content": "</code>",
+    "128257": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
   "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "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": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
   ],
-  "bos_token": "<bos>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<eos>",
-  "model_max_length": 2048,
-  "pad_token": "<pad>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }