初始化项目，由ModelHub XC社区提供模型

Model: concedo/Vicuzard-30B-Uncensored
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,16 @@
+---
+license: other
+language:
+- en
+---
+
+# Vicuzard-30B-Uncensored
+
+This is an experimental mixed model containing a parameter-wise 50/50 blend (weighted average) of [ehartford/Wizard-Vicuna-30B-Uncensored](https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored) and [ehartford/WizardLM-30B-Uncensored](https://huggingface.co/ehartford/WizardLM-30B-Uncensored)
+
+[GGML models are provided here, for use in KoboldCPP](https://huggingface.co/concedo/Vicuzard-30B-Uncensored/tree/main/ggml). 
+
+This improves on earlier model mixing techniques by only applying the merge to the layers containing tensors of the same dimensions. 
+By selectively skipping merge operations on the input and output layers, we are now able to merge models with different vocab sizes (i.e. added tokens) so long as the hidden layers have identical sizes.
+
+All feedback and comments can be directed to Concedo on the KoboldAI discord.

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/home/mixer/concedo/wizlm",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6656,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 52,
+  "num_hidden_layers": 60,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0"
+}

ggml/ggml-model-q4_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3b5e5f9fa0dc4f0295a304e2ef69237cde98fc32c0419e6b4b95cfd8b30689
+size 18300774080

ggml/ggml-model-q4_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725639e443a3c2923b135fa78c3423d097fa973bc876dff1ee653f984c2562b0
+size 20333783552

ggml/ggml-model-q5_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878407093d067f482fa3cee2c2dd398339f59aac183c3b37e7c900f21a4c101a
+size 22366793024

ggml/ggml-model-q5_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31fc98846f22e1d46c1317563e960f3f056f378c8640811568b8a06ac9e0562c
+size 24399802496

pytorch_model-00001-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae78039b406699b7557d1c79606571f7544d51ae299e812bc8d0702e2b86045
+size 6130928659

pytorch_model-00002-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f0a5f09b87e73952e73375db4806d79dbd489cdfd370b34ccc40ba9b7c316d
+size 6243401877

pytorch_model-00003-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f676b9aeddf59c6eb1f280645819f365c935c7cf31dade768145a837e22a6b41
+size 6243402511

pytorch_model-00004-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0f7d21748dceef35fbf814e2c52b130e008dad6abc7403b557b20b959cc57c
+size 6182033817

pytorch_model-00005-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16a33cba8e4a6e910c3f762ea5e86b3464b3ae1df06aace30a8691d74290122
+size 6182061117

pytorch_model-00006-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529032b0eb688108e1615781e75ee0c60d2f3d66584932848bce029b5905c3b6
+size 6182061165

pytorch_model-00007-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c8f441b2f6c0f1c71f318ae33f52eceae0bae738b094c40fde7b5c35a8e852
+size 6243401941

pytorch_model-00008-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb25aef4d49b1a1a8eb9614bc63786e84a21d65ace845097fc49e1194bf61f37
+size 6243402511

pytorch_model-00009-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2140dadcef94c2b9f4626da1b98336d69e9548e8166e030dff0fef51ac3dcc
+size 6182033817

pytorch_model-00010-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc40ddeee232a62c27a8067d0ac639a0812bff8b50d1b5e67caaad9ef89626d
+size 6182061117

pytorch_model-00011-of-00011.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8c14ebd5cc0f90b205996e4d1dacb9557e6fa5a1300089f4719b0e453ae5de
+size 3043345443

pytorch_model.bin.index.json

@@ -0,0 +1,610 @@
+{
+  "metadata": {
+    "total_size": 65057929216
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00011-of-00011.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00011.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00011.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00011.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00011.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00011.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00011.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00011.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00011.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00011.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00011.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00011.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00011.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00011.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00011.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00011.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00011.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00011.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00011.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00011.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00011.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00011.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00011.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00011.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00011.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00011.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00011.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00011.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00011.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00011.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00011.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00011.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00011.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00011.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00011.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00011.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00011.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00011.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00011.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00011.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00007-of-00011.bin",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00011.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00011.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00011.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00011.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00011.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00011.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00011.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00011.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00011.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00011.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00011.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00011.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00011.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00011.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00011.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00011.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00011.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00011.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00011.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00011.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00011.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00011.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00011.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00011.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00011.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00011.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00011.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00011.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00011.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00011.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00011.bin",
+    "model.norm.weight": "pytorch_model-00011-of-00011.bin"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}