Upload folder using huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+base_model:
+- TheDrummer/Cydonia-22B-v1.1
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# out
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [TheDrummer/Cydonia-22B-v1.1](https://huggingface.co/TheDrummer/Cydonia-22B-v1.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: TheDrummer/Cydonia-22B-v1.1
+        layer_range: [0, 29]
+  - sources:
+      - model: TheDrummer/Cydonia-22B-v1.1
+        layer_range: [41, 56]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TheDrummer/Cydonia-22B-v1.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 44,
+  "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": "4.47.0",
+  "use_cache": false,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+      - model: TheDrummer/Cydonia-22B-v1.1
+        layer_range: [0, 29]
+  - sources:
+      - model: TheDrummer/Cydonia-22B-v1.1
+        layer_range: [41, 56]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1499e4f17f8ba1154980cd94bf588855c482f066627cc143f5542199b5ffe2
+size 805318992

model-00002-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5556da7aba70351509ee4a1515470a65da1fafa03aa753d2d2c6f70d55a1cd8
+size 981492888

model-00003-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea7f3f38038f84fb6ebee41af62e46ce577caaed9f8b32463ffa53f519fda9e
+size 981492888

model-00004-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660ade46c589e43d67a969e561db39a69105e4ec3ecb34bd24e1d99c2a893412
+size 994088328

model-00005-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d7a51e142cb662ad5c5825842b3099f5a604f603f704ada2fcbfb23f67a79f
+size 943756792

model-00006-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc0df3d805f76256d695da805f23bc1d004930978ae08395a0ad4d97fdc7f60
+size 981492896

model-00007-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d8349747f4f7d690194822bfb69f4b37c05c92cefdde9f720308686b5b0d17
+size 981492896

model-00008-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d2f197102ac21d2059fb85cd2038a726a608ef3d26481e424e843df2deef88
+size 994088328

model-00009-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4aab0834aa4e31825f2dfb03ea4626ee09ed0c2a6e26737f001d9da6a72101
+size 943756792

model-00010-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f2936fe8fffb80e023de05c3a74ff418a6a9e381d4d4402ec0b6635a9172ee
+size 981492896

model-00011-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f9d34cf5ac6180de182bc095b5ed5a0de26c677d8f36f227c9dae75091e10a
+size 981492888

model-00012-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979d44f80352e0bd47ce3b823d3f1be4a415176152770340bcb8328ebf90e2ef
+size 994088320

model-00013-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881c647146ebdd1b0db16e66ce1b193208d7940b555fe78ecae2b151129afa29
+size 943756792

model-00014-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3e117c23c2f3576af02cc116b8c1a3a6ae54d0eed981cdcb913fa2579a1e46
+size 981492896

model-00015-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f22adc2a2e4dbea727b3d92d9bd672222e99b2f44630c50289fc184ecb529e1
+size 981492896

model-00016-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68662af8f159dcc465143b6b5f7c756975cbf7191075a688a123ff95bd89fea
+size 994088328

model-00017-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0927228fa6b76df8ff61aa0eea1de3fa065df08ab6fb541b96ab426d01c158
+size 943756792

model-00018-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a3d2183ba71be5eeb32eb79b7afce86c3ac02ebe269970a3526e1fd6dc79df
+size 981492896

model-00019-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687627541ca5412ab8662fda36089530dbe5af20446501abeaec9d3397573051
+size 981492888

model-00020-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9892e80a8f0edb2e7d9e2862b54368b64fe6bdb0b949fed7c62b5dcdbba7b7
+size 994088312

model-00021-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5766f30894a3e755850e42f1f3293a3ce0a4f6483aa4f48180cfda17a56189
+size 943756776

model-00022-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e7f0687984e9be79b92a89418a41b9fbe262bf8bb11a0d8d0d42d86e834273
+size 981492896

model-00023-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8f25256fcc2e7cdb44d8c1b40a625d2c7ae0d7f399b6cbec18858b011c4670
+size 981492896

model-00024-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40cb7f688b69a5930bb7e8971643ff6d102e51aca2cfcd609212d948253edfc
+size 994088328

model-00025-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da098c791cce9e33111e4a6e3355b9188e85a50ab7e36c957e7da5ec2046bb7c
+size 943756792

model-00026-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a148a3d48773ec55257b81408ebe5ce009d5f3a6f5f2abc0891a8bac1861a78e
+size 981492896

model-00027-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade9f8c78b9b14251b7aad9407f2b14d902289baff3921a23d5998170eaf0c48
+size 981492896

model-00028-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df77e8089064b911cb9060ed74ea0272d84051e902cb059800806be33a4741cf
+size 994088320

model-00029-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a84ce4c20ff59012cb54b626bd87c7bc75bb14582823eb742bff6dcc4b02aa
+size 943756776

model-00030-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd919b943757434cadf1c924ab801d81f0f7574f6c0b5278ca7b01fadd93e27c
+size 981492896

model-00031-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06eccebbc320b88a6937a931c13bd10d568267fbe2925562a82d2d4d19a64ff6
+size 981492896

model-00032-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df03fd9a26896197dc99d99beed3472551e7b0fe75da170b5034bcc983381613
+size 994088328

model-00033-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f4aa33411cd2d20d0323058b6fa975f7bd5704e5172a924090538435e717f9
+size 943756784

model-00034-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247a853af37e90871327cdfd90a93dd95d51bc62661318b5221bd7d26b60f9f8
+size 981492888

model-00035-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04dbaf03745a2b5795d6e3d9a9fa29fd317b4e8a11749d1814be9a14b23a7a5
+size 981492888

model-00036-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d83c9d40ba447fcae2acfc03d405fabac7c7a73a0bb002b9a27b2b936230835
+size 994088312

model-00037-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226efdd175db2ece2e8373c824da7f95f5420b01cfd3b5520d91bbbae0f78e44
+size 163590608

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 35132583936}, "weight_map": {"lm_head.weight": "model-00001-of-00037.safetensors", "model.embed_tokens.weight": "model-00001-of-00037.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00037.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00037.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00037.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00037.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00037.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00037.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00037.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00037.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00037.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00037.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00037.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00037.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00037.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00037.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00037.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00037.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00037.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00037.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00037.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00037.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00037.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00037.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00037.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00037.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00037.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00037.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00037.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00037.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00037.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00037.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00037.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00037.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00037.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00037.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00037.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00037.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00037.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00037.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00037.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00037.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00037.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00037.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00037.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00037.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00037.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00037.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00037.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00037.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00037.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00037.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00037.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00037.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00037.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00037.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00037.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00037.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00037.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00037.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00037.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00037.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00037.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00037.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00037.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00037.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00037.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00037.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00037.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00037.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00037.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00037.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00037.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00037.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00037.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00037.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00037.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00037.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00037.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00037.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00037.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00037.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00018-of-00037.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00037.safetensors", "model.layers.3.input_layernorm.weight": "model-00019-of-00037.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00037.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00019-of-00037.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00037.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00037.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00037.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00037.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00037.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00020-of-00037.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00037.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00037.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00020-of-00037.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00020-of-00037.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00020-of-00037.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00037.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00037.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00037.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00037.safetensors", "model.layers.29.input_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00021-of-00037.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00037.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00021-of-00037.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00037.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00037.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00037.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00037.safetensors", "model.layers.30.input_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.input_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00037.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00023-of-00037.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00037.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00037.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00037.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00037.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.input_layernorm.weight": "model-00023-of-00037.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00024-of-00037.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00024-of-00037.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00024-of-00037.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00024-of-00037.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00024-of-00037.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.input_layernorm.weight": "model-00024-of-00037.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00024-of-00037.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00025-of-00037.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00025-of-00037.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.input_layernorm.weight": "model-00025-of-00037.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00037.safetensors", "model.layers.35.input_layernorm.weight": "model-00025-of-00037.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00026-of-00037.safetensors", "model.layers.36.input_layernorm.weight": "model-00026-of-00037.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00026-of-00037.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00027-of-00037.safetensors", "model.layers.37.input_layernorm.weight": "model-00027-of-00037.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00027-of-00037.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00037.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00028-of-00037.safetensors", "model.layers.5.input_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00028-of-00037.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00028-of-00037.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00028-of-00037.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00028-of-00037.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00029-of-00037.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00029-of-00037.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.input_layernorm.weight": "model-00029-of-00037.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00029-of-00037.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00029-of-00037.safetensors", "model.layers.39.input_layernorm.weight": "model-00029-of-00037.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00030-of-00037.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00030-of-00037.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00030-of-00037.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00030-of-00037.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00030-of-00037.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00030-of-00037.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00030-of-00037.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00030-of-00037.safetensors", "model.layers.40.input_layernorm.weight": "model-00030-of-00037.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00030-of-00037.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00031-of-00037.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00031-of-00037.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00031-of-00037.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00031-of-00037.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00031-of-00037.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00031-of-00037.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00031-of-00037.safetensors", "model.layers.41.input_layernorm.weight": "model-00031-of-00037.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00031-of-00037.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00031-of-00037.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00032-of-00037.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00032-of-00037.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00032-of-00037.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00032-of-00037.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00032-of-00037.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00032-of-00037.safetensors", "model.layers.42.input_layernorm.weight": "model-00032-of-00037.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00032-of-00037.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00032-of-00037.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00032-of-00037.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00032-of-00037.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00032-of-00037.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00033-of-00037.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00033-of-00037.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00033-of-00037.safetensors", "model.layers.43.input_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00033-of-00037.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00033-of-00037.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00033-of-00037.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00033-of-00037.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00033-of-00037.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00033-of-00037.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00033-of-00037.safetensors", "model.layers.6.input_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00034-of-00037.safetensors", "model.layers.7.input_layernorm.weight": "model-00034-of-00037.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00034-of-00037.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00035-of-00037.safetensors", "model.layers.8.input_layernorm.weight": "model-00035-of-00037.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00035-of-00037.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00035-of-00037.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.input_layernorm.weight": "model-00036-of-00037.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00036-of-00037.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00037-of-00037.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00037-of-00037.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00037-of-00037.safetensors", "model.norm.weight": "model-00037-of-00037.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583