Upload 29 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Undi95/Toppy-M-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+    - model: Walmart-the-bag/Misted-v2-7B
+      layer_range: [0, 24]
+  - sources:
+    - model: Undi95/Toppy-M-7B
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8ca399345ec0fe06e88f9b0173d19a9dcf7e26f86ec8c238ec803405479f6d
+size 960521552

model-00002-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d2c5a3189a6fd85df668f949f178095a742e6c9cc1328020b66d62280423ff
+size 905995864

model-00003-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0a248be43c53374f8580b6a845abc34e569360c140932ebeb380292d57d1f8
+size 989890728

model-00004-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5c96b719b33186f1791bab9be92418542a44cb10aa3bf3f529d9697206cce8
+size 998296072

model-00005-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3208fb9568b2d9149bc446bd69a4ed58135ceb991ffd7a19b2bafcd9b383a8
+size 981502456

model-00006-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3b8856062b4f520effa4ad64af3c64ee769aaa7e132f53b12b6378e52c366c
+size 922798696

model-00007-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1b8ec1592a2bbeb872261304662419effdad9c3b19034ad5f64f0e9850400d
+size 989890728

model-00008-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d4fca0402e823e97ffc1e5fd2892c78ebc89927b23362d650147dd2d68aab8
+size 989890728

model-00009-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a10a9348c51ed7c000857696558f1a43076167b9d2cb0b0aa52dcaf9144091
+size 989890728

model-00010-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09c6884e80cdb9ae5073798addab0c9faf897aa6327f7a2c49e8bb31cbd2a30
+size 989890728

model-00011-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f713eb8e87bcb76d67352174463608f876314bf5ddea379d1ed7f19304951b20
+size 956353248

model-00012-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1834203a8ab277e9810ffa0cad4522e0b239085e2965d6bedaf634b72349d835
+size 989890728

model-00013-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a02e08fcec857832ae6a16c1c9dd9c6c31345ccd6c83ffdde2182fcb91059d1
+size 989890728

model-00014-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cbc667ebe60ce86b6032432ee0ac8a0cb6604493f558d3cc621b708bd80a857
+size 989890728

model-00015-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d793d20fb7a714ff18dd4316409bf367c2e65e15ada8d87a73a30ef460d12063
+size 956344952

model-00016-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42547b7fc263a44047a37742ca50fc4dc77c46151901015f8202dd5ca1d3e731
+size 989890728

model-00017-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d138a38d0f5c3d969016d80bfc6b507313016e62c3f7ec59c818b475482584
+size 998287760

model-00018-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a406deaf060e2df476404421b5950902d00a7e58611f664628f97c4a36dbf6
+size 947956208

model-00019-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b48a720601e712dbe9c2397ad5c5b31d4498f9020975fac5736af8bace56d6
+size 989890704

model-00020-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a091462fb6c6d12cd7126bc555e0f77f45f68423178a3736446ff87b1dbd884d
+size 989890712

model-00021-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c5a25c95ab26d4c2cab5fff0b85295cfd8ad12d3a8a73e5f1d975c8f2826ee
+size 989899016

model-00022-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24dfbdfcbe096a82fc1cc738c5b00ea671704ce146fe9c7aba7178f1fdac0a35
+size 956344912

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 21463048192}, "weight_map": {"lm_head.weight": "model-00001-of-00022.safetensors", "model.embed_tokens.weight": "model-00001-of-00022.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.norm.weight": "model-00022-of-00022.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}