Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- yanolja/EEVE-Korean-Instruct-10.8B-v1.0
+- ai-human-lab/EEVE-Korean_Instruct-10.8B-expo
+---
+
+# Merge-EEVE-10.8B
+
+Merge-EEVE-10.8B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [yanolja/EEVE-Korean-Instruct-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0)
+* [ai-human-lab/EEVE-Korean_Instruct-10.8B-expo](https://huggingface.co/ai-human-lab/EEVE-Korean_Instruct-10.8B-expo)
+
+## 🧩 Configuration
+
+'''yaml
+slices:
+  - sources:
+    - model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
+      layer_range: [0, 48]
+    - model: ai-human-lab/EEVE-Korean_Instruct-10.8B-expo
+      layer_range: [0, 48]
+merge_method: slerp
+base_model: ai-human-lab/EEVE-Korean_Instruct-10.8B-expo
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+'''

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "ai-human-lab/EEVE-Korean_Instruct-10.8B-expo",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 40960
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+slices:
+  - sources:
+    - model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
+      layer_range: [0, 48]
+    - model: ai-human-lab/EEVE-Korean_Instruct-10.8B-expo
+      layer_range: [0, 48]
+merge_method: slerp
+base_model: ai-human-lab/EEVE-Korean_Instruct-10.8B-expo
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebdc5971eccd78c1bdd8d3f67a15240bbfa6e8b842c64334aa51e33c6772e2d
+size 905978424

model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ec0f5e0b8b5226905589e6224fb6c49130df1167b3a0c786c16a821fdfae2
+size 998287744

model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9216e82007eaf9e233cee58618d20d51e84c89ce5eb5d2790b678b5a585df3f
+size 947956216

model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ecc11063e1a9a1e3ddddc5a3dce03e4627f4c1a80be9cf6c30ae22a33d2331
+size 989890728

model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9295be9646c6605bf5105d3abbd9577bc30f7dc3cc36d46b002c56e40bfbf8
+size 989890728

model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae0f682ec5f52080da3ffd681b7f9496befe16cb8c93666f24811e8161cea0f
+size 998287760

model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb64147954dabc0f458acc8d6d1a9f2e6ffe1c678da939e93db0334cc3466680
+size 947956208

model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0cc93481c3c59cadef943a5eb43c0e3a4eac2481bf5c4d33747468089897b91
+size 989890728

model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708dc932709c98ad7e4e497a40d9bce8c0b9e03fe98114b05a5e949f0923a2df
+size 989890728

model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c5a44f6330ccd1c22401a573fd2a74eb4168a9f95ddbbdbd876cf3cd6d9775
+size 998287760

model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff21404dc8be27ad10f8c7125243131705c4d08cca898847058dc9aef5f8726d
+size 947956216

model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52631964f575cf8f419a8da67242f8402dd9587ddafa2907f94ceedc25fb547
+size 989890720

model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02ae79ffc99980e80ecf46b6b3a56ed243e0b0a67749f78f99f26f1af0a2888
+size 989890728

model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8fa49ff46a0a4653c71ceba0cfbadaaa00d5fa4e6f39f561c9d9a8010950604
+size 998287760

model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c695a9b0817595ded8adfa5166971d5dfb1f2912c40fe0114f196ad4d38290
+size 947956216

model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f87cb0029cb0169c6d84d84e619cc495c0b4214aedb0f3b251f70399d7773b0
+size 989890728

model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4d810868f6f6ca3e5aab1991c5b24b2c1fc44d967541575b51ebd46c9c021d
+size 989890720

model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d08fe7097ea87487f16c021e03c5b55acad8aa74a8ebd4ba83f80ad0e6142f1
+size 998287760

model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c884a7f7eb41705ba7aff2064b81f757a270009f27856ce01966e5a956857911
+size 947956216

model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb6e0669bd910051548277ef20ad58eac855338e0d8fb47f2afbabc4f514d9c
+size 989890728

model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ddc29c6d4838b5eb050beb3c9d0deed205f4c0ff6ba5d941c5ceced0a0ad6d
+size 989890712

model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa17721f997223af79da2103a1f7e3bc4f2dd78601c4f3a20c8a554d2f0d9865
+size 998287736

model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:070beb6bad6965458f5774b73631e3a91dc1edd77d1db90f7266481c6a23ca15
+size 75506128

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 21609848832}, "weight_map": {"lm_head.weight": "model-00001-of-00023.safetensors", "model.embed_tokens.weight": "model-00001-of-00023.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.norm.weight": "model-00023-of-00023.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}