BlackSheep's Final CheckPoint : Needed To Clear Up Storage Space

Note: This is not a new fine tune, this training took place in Febuary, I just didn't upload this checkpoint as I did not get it Red-Teamed back when I was practicing HardAblation. YMMV

config.json

@@ -1,14 +1,11 @@
 {
-  "_name_or_path": "models/BlackSheep-24B",
+  "_name_or_path": "examples/Mistral-Abliterated-24B",
   "architectures": [
     "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": [
-    2,
-    131072
-  ],
+  "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 5120,
@@ -23,8 +20,8 @@
   "rope_theta": 100000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.2",
-  "use_cache": false,
-  "vocab_size": 131074
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 131072
 }

model-00001-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c096c9fb8fd1c63e630023477dac9d10782815fc97f9718437cb83cda03f44
-size 4781592216
+oid sha256:624d7722803d77ef11af97667484eda2ed9ce09e5cad92e0b47d56ea7f74d3df
+size 4907389296

model-00002-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba429da82237e1126d2265eba657a9935c542ee02485dfdeebe57cbd2ffc9217
-size 4781592784
+oid sha256:6b2aaa9d1d3474684f7adbead8050b9ae8f112c5385ff205c3bd72512e39303f
+size 4781592792

model-00003-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb06b63bca848a8fdb9481faef26564b2a07fad89dea99d9bca5d4a7307ec708
-size 4781592800
+oid sha256:12dd0fd7af8f1e8ef1726a2667e94d32c2117bf03a23de0b17dbeb95d56cf064
+size 4781592784

model-00004-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252715a4b6c0e76a0c34a10507249c7b29c02ff2a109396d87e41dc553e43dbc
-size 4886471600
+oid sha256:9293720e34dcca85c2d267a976c34ee6831e756a9869cf0b2768e4dec674ebe7
+size 4886471552

model-00005-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8391f15415ec68fb3c10a57f45cfd01bc91b5166cf693b0192af23fe11e640
-size 4781592824
+oid sha256:1044adf57546689e343ac14ac4b31ac69ab34f1d64c660954b1db8d2af6b6c65
+size 4781592792

model-00006-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9cb5065918305846cc2faf9cf418e85d34a1647298d6e9156d4c715d3d57169
-size 4781592816
+oid sha256:5f12473707f0414efc2aad8f79bac9a565147b67357ef9f63c8117270a874e83
+size 4781592776

model-00007-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0b0b799378f9c9391071c3fe2568902f44a256841baf73861cea27b8fba1f6
-size 4886471600
+oid sha256:5a511a826ce20eff382355bfe048b5f6fc19ab361945a22f5a66565ab1d1bf57
+size 4886471552

model-00008-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44deca79f898b30af2928e45ce3d465a0e4024a90d45a1a9ab8e8ec2dc5b02f5
-size 4781592824
+oid sha256:5e710d45ced758b7dcb757597705ac57dafe70ca6e0985f9c9d4664d758d3c84
+size 4781592792

model-00009-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d205e9fa1ea422850cd855f17b586ceeeb2a0dfebb2670e00dcd5d4b9b8083ef
-size 4781592816
+oid sha256:69afdcc0d268209496cfac598bc32273507f422d3506bb61e54fe286654fdef3
+size 4781592760

model-00010-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e093afb167d1d9de069ff8375a5669108adfef35b06dbbeafbed7350e11429
-size 3900797552
+oid sha256:8f763ff109e6e6ea4399689358431aa60f507da96dfa074c7fc266583a3d0748
+size 3774959424

model.safetensors.index.json

@@ -1,370 +1 @@
-{
-  "metadata": {
-    "total_size": 47144847360
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00010-of-00010.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
-    "model.norm.weight": "model-00010-of-00010.safetensors"
-  }
-}
+{"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors"}}

special_tokens_map.json

@@ -1009,14 +1009,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575ad6971cfda40b8c4117b03dcc6875214d1fc2fabf3bc29241ffa13eb611f6
-size 17078414
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

tokenizer_config.json

@@ -8002,22 +8002,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "131072": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "131073": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "additional_special_tokens": [
@@ -9023,13 +9007,12 @@
     "<SPECIAL_999>"
   ],
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{%- set today = strftime_now(\"%Y-%m-%d\") %}\n{%- set default_system_message = \"Mistral Small 3, an Uncensored Large Language Model created by TroyDoesAI. The current date is \" + today + \".\\n\\nWhen not sure of some information, say I don't have the information.\\nIf the user's question is not clear, ambiguous, or does not provide enough context to accurately answer the question, do not try to answer it right away, ask the user to clarify their request (e.g. \\\"Where can I get some good ass tacos near me?\\\" => \\\"Where are you?\\\" or \\\"When's the next flight to Tokyo\\\" => \\\"Where you traveling from?\\\")\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = default_system_message %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n    {%- if message['role'] == 'user' %}\n        {{- '[INST]' + message['content'] + '[/INST]' }}\n    {%- elif message['role'] == 'system' %}\n        {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- message['content'] + eos_token }}\n    {%- else %}\n        {{- raise_exception('Only user, system and assistant roles are supported!') }}\n    {%- endif %}\n{%- endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "</s>",
   "extra_special_tokens": {},
   "legacy": true,
-  "model_max_length": 32768,
-  "pad_token": "<pad>",
+  "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false