yeontaek/llama-2-70b-IA3-guanaco
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: yeontaek/llama-2-70b-IA3-guanaco
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 07:39:37 +08:00
commit 73d5b7d472
26 changed files with 94382 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.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
*.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

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "meta-llama/Llama-2-70b-hf",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}

3
pytorch_model-00001-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0fd65d754bec2f69c0f607fd85d8208fa688d24d7a9cbfa9adc965722352cfd6
size 9718351039

3
pytorch_model-00002-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:910384fcc8ba893ac551e72294333402bcc4de84f9fc69cc67da837e464956fb
size 9798041191

3
pytorch_model-00003-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:689ad41f7b64ccf68692361f986445656555af40f97f8ecb634e673c0051f681
size 9999401955

3
pytorch_model-00004-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:93b9bafc8aeaa084c82f50e042372291935d8a9e593d63d3a2cd2a4ac230cdc2
size 9932259891

3
pytorch_model-00005-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f326cfb46204983e43185c5dea85d0af5816218253658f8788d4a9ad196a21b0
size 9999402019

3
pytorch_model-00006-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc9f5e3865cd0da92ab07464d8f78fa4bb0ee0322481b2e3194323fcae6fe8df
size 9932259891

3
pytorch_model-00007-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbea59d62ccb96703477194bf91e2d475eed6a83fa11abae211bc1f5b8976990
size 9999402019

3
pytorch_model-00008-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f50fe234a8144f29fc5dfd991d99fda5b4aefb70253114985ef067f17b240df
size 9932259891

3
pytorch_model-00009-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d9e057fa7678ea77d53032a5faf44c080e9d178c81a3d59202ff63a9d3d90e1a
size 9999402019

3
pytorch_model-00010-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74f6d757992e1985f9093235e6465fb6235a389356826a62ca1a8625d1afad1a
size 9932259891

3
pytorch_model-00011-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fed84fcd1705cf5274b8bc763ab71748a623d97a5bb5e31775a66bcb0cd4814a
size 9999402019

3
pytorch_model-00012-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4252f7556d76b84edbe2412db392da22f3f59cd91cb9eae1d36c0ffc90ded85
size 9932259891

3
pytorch_model-00013-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc9f0a868dfc5c3a2ae7a9a9b541809bdad47472d7fd844c436a1f5b883f8fd2
size 9999402019

3
pytorch_model-00014-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d67b0f620ce378385db0d3162c16fa2dfd3b715ff3c806f8d74a691fb9f49e35
size 9932259891

3
pytorch_model-00015-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d78ebfb5ca20f39b88aeeb74e10b6d99bbd9024dab18466f61ff99b619e9955
size 9999402019

3
pytorch_model-00016-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bce391bf02a5a8dcccd0936393000d7589c0ac2c78205b6a91d34385d020da6f
size 9932259891

3
pytorch_model-00017-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9763b4c223d3984bb2f24cd929670de5e7ca1930786197a68e5bf8a35e2bed2
size 9999402019

3
pytorch_model-00018-of-00018.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f9dbe030f7ee885025beb7fb05c258deb16b8777886c6f233ebe6d852133ae5
size 9181493725

810
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,810 @@
{
"metadata": {
"total_size": 178218635264
},
"weight_map": {
"lm_head.weight": "pytorch_model-00018-of-00018.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00018.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00018.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00018.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00018.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00018.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00018.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00018.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00018.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00018.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00018.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00018.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00018.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00018.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00018.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00018.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00018.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00018.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00018.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00018.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00018.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00018.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00018.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00018.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00018.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00018.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00018.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00018.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00018.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00018.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00018.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00018.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00018.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00018.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00018.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00008-of-00018.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00018.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00018.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00018.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00018.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00018.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00018.bin",
"model.layers.40.input_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00018.bin",
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00009-of-00018.bin",
"model.layers.41.input_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00018.bin",
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.input_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00018.bin",
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.input_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00018.bin",
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.44.input_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00018.bin",
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00010-of-00018.bin",
"model.layers.45.input_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00018.bin",
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.input_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00018.bin",
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.input_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00018.bin",
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.input_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00018.bin",
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.49.input_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00018.bin",
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00011-of-00018.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00018.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.50.input_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00018.bin",
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.input_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00018.bin",
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.input_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00018.bin",
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.53.input_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00018.bin",
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00012-of-00018.bin",
"model.layers.54.input_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00018.bin",
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.input_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00018.bin",
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.input_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00018.bin",
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.input_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00018.bin",
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.58.input_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00018.bin",
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00013-of-00018.bin",
"model.layers.59.input_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00018.bin",
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00018.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.60.input_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00018.bin",
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.input_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00018.bin",
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.62.input_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00018.bin",
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00014-of-00018.bin",
"model.layers.63.input_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00018.bin",
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.input_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00018.bin",
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.input_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00018.bin",
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.input_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00018.bin",
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.67.input_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00018.bin",
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00015-of-00018.bin",
"model.layers.68.input_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00018.bin",
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.input_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00018.bin",
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00018.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.70.input_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00018.bin",
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.71.input_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00018.bin",
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00016-of-00018.bin",
"model.layers.72.input_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00018.bin",
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.input_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00018.bin",
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.input_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00018.bin",
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.input_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00018.bin",
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.76.input_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00018.bin",
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00017-of-00018.bin",
"model.layers.77.input_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00018.bin",
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.input_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00018.bin",
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.input_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00018.bin",
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00018-of-00018.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00018.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00018.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00018.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00018.bin",
"model.norm.weight": "pytorch_model-00018-of-00018.bin"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

93391
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
size 499723

33
tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}