Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+
+Just a quick slerp merge of 2 Yi 200K models.
+
+# Tess20-RPMerge-Merge
+
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* migtissera_Tess-2.0-Yi-34B-200K
+* brucethemoose_Yi-34B-200K-RPMerge
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: /home/alpha/Models/Raw/brucethemoose_Yi-34B-200K-RPMerge
+  - model: /home/alpha/Models/Raw/migtissera_Tess-2.0-Yi-34B-200K
+merge_method: slerp
+base_model: /home/alpha/Models/Raw/migtissera_Tess-2.0-Yi-34B-200K
+parameters:
+  int8_mask: false
+  t:
+    - value: 0.5
+dtype: bfloat16
+tokenizer_source: model:/home/alpha/Models/Raw/brucethemoose_Yi-34B-200K-RPMerge
+
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "migtissera_Tess-2.0-Yi-34B-200K",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 64000,
+  "eos_token_id": 64001,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 64002
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+models:
+  - model: brucethemoose_Yi-34B-200K-RPMerge
+  - model: migtissera_Tess-2.0-Yi-34B-200K
+merge_method: slerp
+base_model: migtissera_Tess-2.0-Yi-34B-200K
+parameters:
+  int8_mask: false
+  t:
+    - value: 0.5
+dtype: bfloat16
+tokenizer_source: model:brucethemoose_Yi-34B-200K-RPMerge
+

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ddb1cc54050f9cadb612edc4f4a0d84622cfcb608643370b17d4892e3df1714
+size 4962008008

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554bc0814edfd5cc6adc1393409de2818845d06dc156ef23d20883f23a1c9b4e
+size 4976675528

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb862c78218a3e099c2d39dd17d9143090f3e0c9e6280231705c2cb1e10c748
+size 4756459760

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3585d8d127c80d6269109350c1109a7b1f9a2ee9765c3c653ab44c00fcf7c904
+size 4991370152

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b09f087ac216a9cf943ec1f4e85cb80554c9955a5edd9a0e9d4678f2a6681f
+size 4756459768

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ec0e3938368a7caa85435ea25d465b903181732b66a9d76e7fa7399f000f58
+size 4756459752

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9492a0b14957383f4e82baecebfc1d7dd2d69243b05a6c5f2f742ebc038462b
+size 4991370160

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1e98039b489821ac06bdfcc121d1ff43a033058d47dc1be3ed136be33e0c9d
+size 4756459768

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28773cb8daf88163a201bba721b37b420246c3c5e6bc05fcf6c991986b91243
+size 4756459752

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7a249777f1ec2d3d89a9bfaf73c39fe5a45d0803006906aef7483214ed66f3
+size 4991370160

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bb01fdc4639d4a7a79d5900a1db77098ea4799ba34052c82d70f279ce2e737
+size 4756459760

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b4b887c0305a37f09ec227a7c7bdc5bcdfa09f082885fcf902227afe908481
+size 4756459760

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b83625e93afdf5865e4715c6fdda69e51b23a8fceafc07c980cf9ed3ddbc14
+size 4991370160

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118d2d06d16b001cb64d36ba67646b9cd81785921e8fe2cad3ba56c05861519d
+size 4756459736

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7d1ef1ac7b9d06d35a488add792ef448b1fde7ece863677d245226ae3c4d7a
+size 822113184

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 68777891840}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 200000,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}