Upload 32 files

.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 +1,56 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# UltraNemo-12b
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the linear [DELLA](https://arxiv.org/abs/2406.11617) merge method using ..\text-generation-webui\models\Mistral-Nemo-Base-2407 as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* ..\text-generation-webui\models\Lyra-Gutenberg-mistral-nemo-12B
+* ..\text-generation-webui\models\mistral-nemo-gutenberg-12B-v4
+* ..\text-generation-webui\models\Violet_Twilight-v0.2
+* ..\text-generation-webui\models\Grey-12b
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: ..\text-generation-webui\models\mistral-nemo-gutenberg-12B-v4
+    parameters:
+      weight: 0.2
+  - model: ..\text-generation-webui\models\Violet_Twilight-v0.2
+    parameters:
+      weight: 0.3
+  - model: ..\text-generation-webui\models\Lyra-Gutenberg-mistral-nemo-12B
+    parameters:
+      weight: 0.5
+  - model: ..\text-generation-webui\models\Grey-12b
+    parameters:
+      weight: 0.2
+base_model: ..\text-generation-webui\models\Mistral-Nemo-Base-2407
+parameters:
+  density: 0.5
+  epsilon: 0.1
+  lambda: 1.1
+  normalize: false
+  int8_mask: true
+  rescale: true
+merge_method: della_linear
+tokenizer:
+  source: union
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "..\\text-generation-webui\\models\\Mistral-Nemo-Base-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 131074
+}

mergekit_config.yml

@@ -0,0 +1,25 @@
+models:
+  - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
+    parameters:
+      weight: 0.2
+  - model: Epiculous/Violet_Twilight-v0.2
+    parameters:
+      weight: 0.3
+  - model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
+    parameters:
+      weight: 0.5
+  - model: aixonlab/Grey-12b
+    parameters:
+      weight: 0.2
+base_model: mistralai/Mistral-Nemo-Base-2407
+parameters:
+  density: 0.5
+  epsilon: 0.1
+  lambda: 1.1
+  normalize: false
+  int8_mask: true
+  rescale: true
+merge_method: della_linear
+tokenizer:
+  source: union
+dtype: bfloat16

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f7f55e96d606fbccbf303cecfd38d6cf8c01456662f1613cc7af68562ed52e
+size 1342197888

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f88486e3142f21c2ff4f3a0cce580ae9fb3b4cc3da26aa9db558d2658c3f37e
+size 1342197904

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb3708374ec390b9783982b24b00c5655d45a504954bc9ae0c864ca0abacf23
+size 996189888

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0db6f698771e7e10618345680c56dfdcdc8e764df7420f538748d6712c04663
+size 933265104

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd15a4bfd46681efe6cbc1819a42a575a604c3da917ac2cbe3c5a0b9a0bc1995
+size 943761344

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f387d2efc1cc2c398af747b843808f8207dd048fe468853295c1f609ef2b33
+size 943761344

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13366cd223fdca1409d3b82eae830c50049b7a27066afc0d8977d3efe6e442a2
+size 996179560

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef17120cd30b7d061a7b22bf953cb7edefd37089e876530e9e17b8c31d25beb
+size 933265104

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5712d646e90f47f5749aa3d51fb9e16f6fa9e92d6044d2a18bad9548b2c5bfe6
+size 943761344

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a86ebfabe7e6c9314808ffbd5a1bcecd047be12e3234ea060a75dc5c9e91617
+size 943761344

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b51d208423713a493ad19177fc98673f32bf79e9592d7b9ddfec779d3f927a7
+size 996179560

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6497ad2f4ae9de0addb99435f703efda99f49cc65b68525b4983e567e60a8b36
+size 933265104

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f415681c67118aa53fc341fd4109c4128a2a0b0676d25aaa3fe1e8eed030838
+size 943761344

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4745e4c032754ca95e557da9946d8d31bf27f5d221e33815490ab78e2805e17
+size 943761344

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6098e5d5a673ab2d0c2bcbd6484ea7103e9418659aa814283a956f21a3eaf7
+size 996179560

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89f6348edf5c4f365e41dfd8ec85b3daa8461fd2c7fcd7874d19949dce7f78e
+size 933265096

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9822a58075cb823b449325ee719f0c2901016b1908f8df5009e1e77b692222a
+size 943761344

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052cd2bf3553e5c2324e7283481237b52f99900d6854040472f8b57d09fbe907
+size 943761344

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4675368283a9d6dd7d8182c7ac4dbd4dc9b794bed2dd6bcdca754a3308a2d87d
+size 996179560

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef525ea5c40e4a04fa4a56339647eaadbb715df6c50788e1fcc8c514b9d60410
+size 933265104

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6428a90e329fe6ba0f6c69cf4e4f8fdf528707a6468184dc7d5383c677f9fcb
+size 943761344

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe80b2f1a1e7d4201dbb03e72e81e49b3c2c36ac9dd60e8a5e746032a9b3648d
+size 943761336

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3f3b6fc023a8576ac6c34eafc8614c80fdb75c2c011db6c9e09c7e1662959c
+size 996179552

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725581cd726c379edf50e47df2b1b346af6409f27a0c3fc44e496fed8ac44678
+size 933265088

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1517e3782ebfa73eea990630c6b09433c52f6b0efdd72b0a40ac136e1b47de1f
+size 796960560

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 24495605760}, "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 sha256:48130f8c042761b84abbfbf10ad07efa7c26108a14e7a2a0402daa06e447a47a
+size 17078668