Upload Psyonic-Cetacean-MythoMax-Ultra-Quality-29B

README.md

@@ -0,0 +1,58 @@
+---
+base_model:
+- Gryphe/MythoMax-L2-13b
+- TeeZee/Orca-2-13b_flat
+- KoboldAI/LLaMA2-13B-Psyfighter2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Psyonic-Cetacean-MythoMax-Ultra-Quality-29B
+
+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:
+* [Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b)
+* [TeeZee/Orca-2-13b_flat](https://huggingface.co/TeeZee/Orca-2-13b_flat)
+* [KoboldAI/LLaMA2-13B-Psyfighter2](https://huggingface.co/KoboldAI/LLaMA2-13B-Psyfighter2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+ - sources:
+   - model: TeeZee/Orca-2-13b_flat
+     layer_range: [0, 16] 
+ - sources:
+   - model: Gryphe/MythoMax-L2-13b
+     layer_range: [8, 20] 
+ - sources:
+   - model: KoboldAI/LLaMA2-13B-Psyfighter2
+     layer_range: [14, 24] 
+ - sources:
+   - model: TeeZee/Orca-2-13b_flat
+     layer_range: [16, 32] 
+ - sources:
+   - model: Gryphe/MythoMax-L2-13b
+     layer_range: [20, 38] 
+ - sources:
+   - model: KoboldAI/LLaMA2-13B-Psyfighter2
+     layer_range: [24, 38] 
+ - sources:
+   - model: Gryphe/MythoMax-L2-13b
+     layer_range: [38, 40] 
+merge_method: passthrough
+dtype: float32
+
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Gryphe/MythoMax-L2-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 88,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,24 @@
+slices:
+ - sources:
+   - model: TeeZee/Orca-2-13b_flat
+     layer_range: [0, 16] 
+ - sources:
+   - model: Gryphe/MythoMax-L2-13b
+     layer_range: [8, 20] 
+ - sources:
+   - model: KoboldAI/LLaMA2-13B-Psyfighter2
+     layer_range: [14, 24] 
+ - sources:
+   - model: TeeZee/Orca-2-13b_flat
+     layer_range: [16, 32] 
+ - sources:
+   - model: Gryphe/MythoMax-L2-13b
+     layer_range: [20, 38] 
+ - sources:
+   - model: KoboldAI/LLaMA2-13B-Psyfighter2
+     layer_range: [24, 38] 
+ - sources:
+   - model: Gryphe/MythoMax-L2-13b
+     layer_range: [38, 40] 
+merge_method: passthrough
+dtype: float32

model-00001-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c530095ec7c902079b83230af063ce0fa0a695f64b66d7fa29bf9d10b92f3d
+size 4980861856

model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f9fd0e5557d58bfcbb9b0bd939bb6757d6624e141feaf82d5793e50739d7a3
+size 4792160232

model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baac9766f975649ce19c0da25258c95339a4f1f60a04e8cb8c826c027c952e61
+size 4792180824

model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c638675a64d245a9e2189617140c647524832dc9df236eaa9e8af1db84e32315
+size 4938919448

model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa855d01ab5cf52a32e2b24c8497b1484863e8867b01fae2a6b848221e42b26
+size 4970438752

model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8e61ef1019ffdc16dab990b5cdb1e71f02fddb9cf20c77a44c4f8c69740073
+size 4750238136

model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96938791df91f8020c6775e612ff4604b33b0ddb3d24b5af3c6d28094f65e83b
+size 4938919448

model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1489af4ae6280e3c58906a937134044cd257a15d5958e877ec34eae1af61a8
+size 4792160216

model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37a0b40c5b3133f247e270c91e05da5f1ba898bb6e22751cd6941babfd91187
+size 4938919440

model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9b387f45bda416d0257c6f0eee23ce723425661e6dbea454fed0dd440e29a1
+size 4897038552

model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bcd06ccc7d2c699ec843968c2bcb5eb4c46cdc8bdc6799bb4924c586395539
+size 4823638336

model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152af4281e614057fcdac10a50cb31c95f8bfe321e0bc83931194626c9f03245
+size 4938919448

model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62458848cc971598dfade92b79f7dfa75fbddf87ce9028765a336ef223e38a22
+size 4938981240

model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44bbc241fd9f7de57c53f30b462bb54bdeeacb5094675518d520e3184cc2626
+size 4959891792

model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3d2005f892bcac0e33ad72e893c7fb9369fe83108d23e581731e27adc1a061
+size 4760723304

model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10a90c2dfdbca9584138bcf3201a58b1602bf137f2181a78a44c7d12749e599
+size 4792160216

model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f861114e904b443e44c66bf105440a9b18c7f46faca465a37ea94fc93f04ece2
+size 4938919448

model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2af374532168424dfe28b480ccc6fd3d3b7b91d688c250e796a5c28096f87c
+size 4928496064

model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b0b366d82642b3d7ebb6b5a59aab9683a5abec5d920192b438253ef466d9bc
+size 4792160240

model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6637abf9e1deab3c05463a5728e45cec880ea0f7af950aedb8f8716982fdcc11
+size 4970376976

model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44da3781f2e6b2a43fae7b5ecb16b2592d8d0b96ed7536de3c7fb9a53adf794a
+size 4970418152

model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b965a43fd38782384727f05fbc1612804bc74168db25d9d22a1a3ff567f79da
+size 4970418112

model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d2fd544699b79e7e9afc856f80f08522aa6a71dd549bf59b537d0bd9623aec
+size 4970418128

model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7d36cef9b62d73f33a4b5b697e497ee444e7aaf81ac906bda2632fa8670c8e
+size 419451464

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 112966717440}, "weight_map": {"lm_head.weight": "model-00001-of-00024.safetensors", "model.embed_tokens.weight": "model-00001-of-00024.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.54.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.55.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.56.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.36.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.57.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.58.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.73.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.59.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.47.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.74.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.60.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.48.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.75.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.61.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.49.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.76.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.62.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.50.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.77.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.63.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.51.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.78.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.64.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.52.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.79.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.65.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.53.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.66.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.67.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.82.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.68.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.83.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.69.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.84.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.70.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.85.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.71.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.86.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.87.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.4.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.7.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.16.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.8.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.17.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.9.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00024-of-00024.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00024-of-00024.safetensors", "model.norm.weight": "model-00024-of-00024.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": "<unk>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}