初始化项目，由ModelHub XC社区提供模型
Model: Austism/chronos-wizardlm-uc-scot-st-13b Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
10
README.md
Normal file
10
README.md
Normal file
@@ -0,0 +1,10 @@
|
||||
---
|
||||
license: other
|
||||
tags:
|
||||
- llama
|
||||
- storywriting
|
||||
---
|
||||
(chronos-13b+(WizardLM Uncensored+CoT+Storytelling))
|
||||
80/20 merge
|
||||
|
||||
intended to be much like chronos with different writing and instruction following capabilities.
|
||||
23
config.json
Normal file
23
config.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "E:/TextGenWebUI/text-generation-webui/training/alpaca-lora/loramerge/wizardlm_scot_st",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.28.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32001
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.28.1"
|
||||
}
|
||||
3
pytorch_model-00001-of-00013.bin
Normal file
3
pytorch_model-00001-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:196a67d8fe673d4cf13e956b1e2cad96cc6048a740722efd4ba45727e1b86bff
|
||||
size 2089348615
|
||||
3
pytorch_model-00002-of-00013.bin
Normal file
3
pytorch_model-00002-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d3e0d47a635803da6efe8e19f70800cac5a09bf27a78f21ad2e61f630e3b1767
|
||||
size 2044816481
|
||||
3
pytorch_model-00003-of-00013.bin
Normal file
3
pytorch_model-00003-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:761047dd74f81c44d8695b4eef4c93178096312b3a9201ec64d06df5c4ebe109
|
||||
size 2060524641
|
||||
3
pytorch_model-00004-of-00013.bin
Normal file
3
pytorch_model-00004-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b52f8401cc2e78d151d48afab0a9a20c653b5ce240848f0051e77cf56540580c
|
||||
size 1955666831
|
||||
3
pytorch_model-00005-of-00013.bin
Normal file
3
pytorch_model-00005-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fd7b2f9e44821875a1c1808323e37850f0408d3178a640bf43f123e95fd55d6d
|
||||
size 2044795325
|
||||
3
pytorch_model-00006-of-00013.bin
Normal file
3
pytorch_model-00006-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b954722f6a1328db852809c4373b6b97c8142063507578dff0a28668b39feb4
|
||||
size 2044795325
|
||||
3
pytorch_model-00007-of-00013.bin
Normal file
3
pytorch_model-00007-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:98f35cb276ba1f4c9fb1f80986525e6f3e8cf403bfb95d486ac385918cb7af59
|
||||
size 2044816481
|
||||
3
pytorch_model-00008-of-00013.bin
Normal file
3
pytorch_model-00008-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7bf29ef58c757649923e618de0ecb3ca3f7b270cae5d5c8ef575259d76d4bc8c
|
||||
size 2060524641
|
||||
3
pytorch_model-00009-of-00013.bin
Normal file
3
pytorch_model-00009-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:30f1e174b0012e153f2000654407fa150ed1a3cadf593853234c94c257f07280
|
||||
size 1955666831
|
||||
3
pytorch_model-00010-of-00013.bin
Normal file
3
pytorch_model-00010-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7a35b1869da0f2ee7460b4a66a60652b56cfc92148bb73ea26898d3f01adcb1c
|
||||
size 2044795325
|
||||
3
pytorch_model-00011-of-00013.bin
Normal file
3
pytorch_model-00011-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5cc1894c6a3a1834b377ce88ff207f3a5b4f608f7970d57f80cea46510f0e91e
|
||||
size 2044795325
|
||||
3
pytorch_model-00012-of-00013.bin
Normal file
3
pytorch_model-00012-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a949a1e9c519279a39cc7d9ab7330ceec0bdf6bd1cd6af297dbdbd4934ce5cd
|
||||
size 2044816481
|
||||
3
pytorch_model-00013-of-00013.bin
Normal file
3
pytorch_model-00013-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8e8687a831a2294c22778f4ed892c73b11ae1ad269906faf335a68611f2f07f2
|
||||
size 1596526107
|
||||
410
pytorch_model.bin.index.json
Normal file
410
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,410 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26031754240
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.norm.weight": "pytorch_model-00013-of-00013.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user