sharpbai/alpaca-7b-merged
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: sharpbai/alpaca-7b-merged
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-30 06:47:19 +08:00
commit 1f1931546e
44 changed files with 93995 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View 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

35
README.md Normal file
View File

@@ -0,0 +1,35 @@
---
license: other
tags:
- alpaca
---
### Stanford Alpaca-7B-Merged
*The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads*
This repo hosts the merged weight for [Stanford Alpaca-7B](https://github.com/tatsu-lab/stanford_alpaca/) that can be used directly.
Below is the original model card information.
-----------------------
### Stanford Alpaca-7B
This repo hosts the weight diff for [Stanford Alpaca-7B](https://github.com/tatsu-lab/stanford_alpaca/) that can be used to reconstruct the original model weights when applied to Meta's LLaMA weights.
To recover the original Alpaca-7B weights, follow these steps:
```text
1. Convert Meta's released weights into huggingface format. Follow this guide:
https://huggingface.co/docs/transformers/main/model_doc/llama
2. Make sure you cloned the released weight diff into your local machine. The weight diff is located at:
https://huggingface.co/tatsu-lab/alpaca-7b/tree/main
3. Run this function with the correct paths. E.g.,
python weight_diff.py recover --path_raw <path_to_step_1_dir> --path_diff <path_to_step_2_dir> --path_tuned <path_to_store_recovered_weights>
```
Once step 3 completes, you should have a directory with the recovered weights, from which you can load the model like the following
```python
import transformers
alpaca_model = transformers.AutoModelForCausalLM.from_pretrained("<path_to_store_recovered_weights>")
alpaca_tokenizer = transformers.AutoTokenizer.from_pretrained("<path_to_store_recovered_weights>")
```

3
added_tokens.json Normal file
View File

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

23
config.json Normal file
View File

@@ -0,0 +1,23 @@
{
"_name_or_path": "sharpbai/alpaca-7b-merged",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.30.1",
"use_cache": true,
"vocab_size": 32001
}

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": "4.30.1"
}

3
pytorch_model-00001-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3aec1f7428942a83387eb237683094a23d23689aadef6fc2dbb1d93d5dfacb3b
size 396372671

3
pytorch_model-00002-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:782c6cfe6773b8e0a299faeb6cb80bf037bab2a6d5bfa1219b5bad7f7f0dddf8
size 404770755

3
pytorch_model-00003-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cec4a07916da78a26890de181c2caa64acba120c159a60f032dde97c4a8c2103
size 404770755

3
pytorch_model-00004-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f0fc49849624a1d09f1a53571c572b6fba1fc7f579c98081ca95f3568f7938e9
size 404770755

3
pytorch_model-00005-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c9cecb98223b8463663fae243df1326d4a39001a0c671683a419ff06b6b1afa
size 404770755

3
pytorch_model-00006-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08aece55bb12927709f91c2ed9d7e308a02190332d2aa9df0e73925adac32aa0
size 404770755

3
pytorch_model-00007-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46b59933c2dadaeba9055320217f4fbba63f235c7eeec33aa9ed14e92df26c99
size 404770755

3
pytorch_model-00008-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4999d51e214b3794bca9fce578d50babececa4f6aa874bd506d904122587f254
size 404770755

3
pytorch_model-00009-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:157538e3f8d6f09e105c8bcc39a02c74be491d74856a798225670172dfd6671c
size 404770755

3
pytorch_model-00010-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e2f1b8e5f5d05f82572fd73c355bf05570b2656a3d3407bb154e58fb46050ec5
size 404770755

3
pytorch_model-00011-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:815e80f3e07fb51896150954615110de2dda32882b7464f5a3161153f9700e6e
size 404770755

3
pytorch_model-00012-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3c718c9f4e0fd09f0d7746d0db5a191cb0c7aa0050e5656acc9101f46c2f24e3
size 404770755

3
pytorch_model-00013-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:df16e77c3cbbefef908354b6aedad2de18c332cce496d54f2ff55ff3cbd61163
size 404770755

3
pytorch_model-00014-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8143cc997e100ae4aa828774738b97399e00ffe25cb1d793e7e4e59ae08a1648
size 404770755

3
pytorch_model-00015-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:272f4d56ddb47e9dab47357e9148f10175ee65b977135606d2b54a8d869a5c3c
size 404770755

3
pytorch_model-00016-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4baff3985ab6c9c89e5ee4455d25ea54280eb566baca8f93e2400bed865a95bc
size 404770755

3
pytorch_model-00017-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d3a2320e956ce306cee05ee8ddf08733c964ad8f7bcdd451c6bf7c5796984479
size 404770755

3
pytorch_model-00018-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fd32f63ced8241184840b7047f2287c9cbbd193e0769320fc4d2660fadc347b
size 404770755

3
pytorch_model-00019-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:947204eb23ecb8e585efa29491b7cb49ee3f07b69efd1b09b51751f9746bf439
size 404770755

3
pytorch_model-00020-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf6251414ac0723b1d4c82cdabe230e6478d61df39ff8a75f5af487f56116f6c
size 404770755

3
pytorch_model-00021-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ec04c0ea3a22035c3642d35cfd585e861d1358950849dc3f6b5da4e15f0a8620
size 404770755

3
pytorch_model-00022-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dfcab1200d267d1db59419cfc5cb93503ba43f3581d47a9f7a9602e4f0e69f34
size 404770755

3
pytorch_model-00023-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a667f05630e2488201f585d589f0a889dec1b010b7449a6a71767297b7cdf89
size 404770755

3
pytorch_model-00024-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5243eb2f34bdd59202e4ce72fb8f83974a8fc57213ada4936b036e2a62175fae
size 404770755

3
pytorch_model-00025-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b624aff546288582a0c9dd2fabd7305e058b5688b57f04f144d7e71d38c6031
size 404770755

3
pytorch_model-00026-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f48b3e1ed617e6b88ed2bb2610c7999d0c7ebc50d9b7c134eb4ae43bee129e78
size 404770755

3
pytorch_model-00027-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4bd72bc047e91da4f1c6c4ec901b2d7bb9329d0b3a21965fcf5ca304a69806d9
size 404770755

3
pytorch_model-00028-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4bd6fe47c611f069c14aa9977e4e0bc26406b543e0dad3f21454cf1413c0a869
size 404770755

3
pytorch_model-00029-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:040e4181522a1f057b261d673ec1685bf6008031ed852bb931213ba5bdc25917
size 404770755

3
pytorch_model-00030-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a76c74ec9f91982ec5c8301798ca76bfc5c08ad8988195361b93e756088f3ce
size 404770755

3
pytorch_model-00031-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dad9b3106ef098686534a58b6bb280dad0d4639e934a58e133baecbc8a359761
size 404770755

3
pytorch_model-00032-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64662501649154dc846910ebd82206d4c025932c5715c9c296a7fc47f0bf8801
size 404770755

3
pytorch_model-00033-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:805c3dc9879f7185e6b068a4214be634a68b4858525dcf7bddd0094d215ef558
size 270559679

3
pytorch_model-00034-of-00034.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bb6d8ac32c0fef962918da1ef9b3a29cf013040f0a183ad8135e6c70d21d31ba
size 262153130

330
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,330 @@
{
"metadata": {
"total_size": 13476855808
},
"weight_map": {
"lm_head.weight": "pytorch_model-00034-of-00034.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00034.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00034.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00034.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00034.bin",
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00034.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00034.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00034.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00034.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00034.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00034.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00034.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00034.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00034.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00034.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00034.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00034.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00034.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00034.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00034.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00034.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00034.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00034.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00034.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00034.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00034.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00034.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00034.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00034.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00034.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00034.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00034.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00034.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00034.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00034.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00034.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00034.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00034.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00034.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00034.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00034.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00034.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00034.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00034.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00034.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00034.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00034.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00034.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00034.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00034.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00034.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00034.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00034.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00034.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00034.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00034.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00034.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00034.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00034.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00034.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00034.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00034.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00034.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00034.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00034.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00034.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00034.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00034.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00034.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00034.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00034.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00034.bin",
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00034.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00034.bin",
"model.norm.weight": "pytorch_model-00033-of-00034.bin"
}
}

24
special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"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
},
"pad_token": "[PAD]",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

93400
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

34
tokenizer_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}