Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+base_model:
+- MarinaraSpaghetti/NemoMix-Unleashed-12B
+- inflatebot/MN-12B-Mag-Mell-R1
+- elinas/Chronos-Gold-12B-1.0
+- Retreatcost/KansenSakura-Eclipse-RP-12b
+- redrix/patricide-12B-Unslop-Mell-v2
+---
+
+# RP-king-12b
+
+RP-king-12b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [MarinaraSpaghetti/NemoMix-Unleashed-12B](https://huggingface.co/MarinaraSpaghetti/NemoMix-Unleashed-12B)
+* [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1)
+* [elinas/Chronos-Gold-12B-1.0](https://huggingface.co/elinas/Chronos-Gold-12B-1.0)
+* [Retreatcost/KansenSakura-Eclipse-RP-12b](https://huggingface.co/Retreatcost/KansenSakura-Eclipse-RP-12b)
+* [redrix/patricide-12B-Unslop-Mell-v2](https://huggingface.co/redrix/patricide-12B-Unslop-Mell-v2)
+
+## 🧩 Configuration
+
+```yamlmodels:
+  - model: MarinaraSpaghetti/NemoMix-Unleashed-12B  # Base model for creative foundation
+    parameters:
+      density: 0.65
+      weight: 1.0
+  - model: inflatebot/MN-12B-Mag-Mell-R1  # For worldbuilding and prose
+    parameters:
+      density: 0.8
+      weight: 1.2
+  - model: elinas/Chronos-Gold-12B-1.0  # For roleplay and prompt adherence
+    parameters:
+      density: 0.9
+      weight: 1.1
+  - model: Retreatcost/KansenSakura-Eclipse-RP-12b
+    parameters:
+      density: 0.5
+      weight: 0.7
+  - model: redrix/patricide-12B-Unslop-Mell-v2  # For anti-GPTism and balance
+    parameters:
+      density: 0.6
+      weight: 0.9
+merge_method: dare_ties
+base_model: MarinaraSpaghetti/NemoMix-Unleashed-12B
+parameters:
+  normalize: true
+dtype: bfloat16
+tokenizer_source: base```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,27 @@
+models:
+  - model: MarinaraSpaghetti/NemoMix-Unleashed-12B  # Base model for creative foundation
+    parameters:
+      density: 0.65
+      weight: 1.0
+  - model: inflatebot/MN-12B-Mag-Mell-R1  # For worldbuilding and prose
+    parameters:
+      density: 0.8
+      weight: 1.2
+  - model: elinas/Chronos-Gold-12B-1.0  # For roleplay and prompt adherence
+    parameters:
+      density: 0.9
+      weight: 1.1
+  - model: Retreatcost/KansenSakura-Eclipse-RP-12b
+    parameters:
+      density: 0.5
+      weight: 0.7
+  - model: redrix/patricide-12B-Unslop-Mell-v2  # For anti-GPTism and balance
+    parameters:
+      density: 0.6
+      weight: 0.9
+merge_method: dare_ties
+base_model: MarinaraSpaghetti/NemoMix-Unleashed-12B
+parameters:
+  normalize: true
+dtype: bfloat16
+tokenizer_source: base

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892399552ba8d8661e549f6a046f859174f411168b54afddf56b0bbd90f625af
+size 1342177408

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c809877e7e6a17b23a588e8b803c73ba00c7bca5c43606843718d45835c5eeae
+size 1342177424

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5014423991c18f234ee4aca48a2ed060c492d5883d32c7bce002d82a7af7600
+size 996189888

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7f4df0b0a383bc3fbdcf4c31649fc8777142f69366dc33149e3be3f79817be
+size 933265104

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5995d9b3480b7fef924ce0c305971e100d89623397078f84bdefe12692f251f
+size 943761344

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29bcaee73d005827b7f32289ec2137110ce34e689c9ed960475f42d11ff9ea1a
+size 943761344

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cd222bed0971ef654fb22d2b7205796b52fd4170530b6434af47525b4ad512
+size 996179560

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af9e285a9ad2ac28580e329b8385cd5b1bf75ad1948e08f25c4b12d65aadc6a
+size 933265104

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0f83c6b463c60574ea66154173e78a9aaa42984988f574dd5499229cc86dec
+size 943761344

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d9760f9f95c026ac7da13d9db7cc8aec6126ff9c643f6e8df3e9622bf1f3ee
+size 943761344

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b32080cad78943adf6bec2051f3e713655c52160b3d549150a391473008214
+size 996179560

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722977eab366874a295eae287acf7b7edbc220fed1d5f2739556130a2f22f1bb
+size 933265104

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caaa7134c11792afa82670a70a14395145ef023040f68fe26f53fa129decb4a
+size 943761344

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5132bd015faa962310d0cfb99f44acd2cdd80fe8bb3e2bbcdca589dca7c612c
+size 943761344

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5775e3c9e5bdab8f1e4efab6e432623af6b099e2754f3e97dcb1ce1527c514
+size 996179560

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b9a86d3cb58e67736be06cc3c4dd59ede7d107e16631150c78a81b4c4bfcc9
+size 933265096

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cba15543c0e6447cc9ee26873d0566ee8ba8dacacfb597f07589c5577b704d
+size 943761344

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ecf68897d952d7b3bbe99c56dd498c5addd740711fa846728bb91992fceccb
+size 943761344

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474dfbc5ab659bb7769588cea58a638d79fd296335f5541ceaa8c6de2ba202e7
+size 996179560

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd187cb23eb05ed660c3aa850179ab799e372cfa45c175561b077d33a1f418b
+size 933265104

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3e35cc12eb16536bac81219783ca53e537855bc8ef806e70d893529a025270
+size 943761344

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d0613b7444f722e0c49c290307bdfa2460d31dc1dc89826038fa798e109520
+size 943761336

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6d32275549576bf404b55fec99554a8a01f32b45ccb431705d98e6535961bc
+size 996179552

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb44f5a90548fa3a76704626d5731310f33381941b3f4c81c2b45edfbd92f84
+size 933265088

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a29bb42e8eb556c36ddcc1428c419984dea9f5e5ad69ad596c9d6985d10e9e
+size 796960560

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 24495564800,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00025.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00025.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00025-of-00025.safetensors",
+    "model.norm.weight": "model-00025-of-00025.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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292