maywell/PiVoT-SUS-RP
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: maywell/PiVoT-SUS-RP
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-23 08:31:14 +08:00
commit 63d3c63dc0
24 changed files with 789 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
.gitattributes vendored Normal file
View File

@@ -0,0 +1,64 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
model-00003-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00014-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00015-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00009-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00008-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00011-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00012-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00010-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00013-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text

20
README.md Normal file
View File

@@ -0,0 +1,20 @@
---
license: apache-2.0
---
## Model Description
PiVoT-RP model based on SUS-34B
Train with LoRA,
Private Dataset used.
Seq Len = 8192.
Super Fast **unsloth used** while training. :>
Follow me on twitter: https://twitter.com/stablefluffy
Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕
Contact me on Telegram: https://t.me/AlzarTakkarsen

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "./synatra_11bv4",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 7168,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 56,
"num_hidden_layers": 60,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"use_cache": true,
"vocab_size": 64000
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

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": "4.36.2"
}

3
model-00001-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:adb3a2a16bc5540697178d5b9b49d9ad5ae8e49648647c0e6dcd92497a81f529
size 4793130760

3
model-00002-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d87430917e6f9f1b2886fd0dd5c7425b8547dba3a11794140c581f984e0e4e95
size 4756459720

3
model-00003-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33626f98ef31905dc251ed426bd7aa4df1deebf31de08316180e1b9ee4be3109
size 4991370136

3
model-00004-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de247e4f01eac395d6b8a2d5339368c284d6af32508438572f3d69a9bda7641b
size 4756459760

3
model-00005-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b1b55a4ac3adc645a16007579da98950ff429340626733f1a0325d827d6c8b8
size 4756459760

3
model-00006-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2fb2ab3b5cb4db59cf9cb38066b0f82bee8a4e7b0035cc830f5458de0959e4e
size 4991370160

3
model-00007-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac38f98e62123a5514452874706b37338fee4c8bb02ddf2384db273a866a4e68
size 4756459760

3
model-00008-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:208e0d2323271d7ccaac4dad5da0ad8cd625a72f00dc33102a94ed1ff0a54bf5
size 4756459760

3
model-00009-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b0f78a7eac8b90ed608ac1e6e57167ffa841b6ead0dbe5e885f356af8b41e04
size 4991370160

3
model-00010-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ccbe916a2de1fa84821602e88b87dd760b5bba78d487170ab3a49d6e75529f10
size 4756459760

3
model-00011-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f38de1f69724e4e6b0f47a8b9c4b626ed3087daf868ca3ff8c4c6dd81ad18b3c
size 4756459760

3
model-00012-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa463eecf06f34dd6b428a5546a30448d35a89196c97d3803f693159b69a264e
size 4991370160

3
model-00013-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0fea393c2affd1aa2f041f51ac5172fb78494d5d3da9333cdbdd98f43d68a7b
size 4756459760

3
model-00014-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f02c5ab14401f4c680f708ddf257b8d1c019825abb351d351cc3f4735fa5b64
size 4756459760

3
model-00015-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3f74319b2a036a8dc6a8cd607ec3a0e3fe4277523749cf745fb4aae41c54de3c
size 1211148856

550
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,550 @@
{
"metadata": {
"total_size": 68777834496
},
"weight_map": {
"lm_head.weight": "model-00015-of-00015.safetensors",
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
"model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
"model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
"model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.norm.weight": "model-00015-of-00015.safetensors"
}
}

30
special_tokens_map.json Normal file
View File

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

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8035748f5ec68ab94ff6a820b1a7a5814e20887f4deacddcf21d5194590bf08f
size 3561371

40
tokenizer_config.json Normal file
View File

@@ -0,0 +1,40 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": true,
"model_max_length": 4096,
"pad_token": "<unk>",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}