teknium/Base-GPT4-x-Alpaca-Roleplay-Lora
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: teknium/Base-GPT4-x-Alpaca-Roleplay-Lora
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-13 21:44:13 +08:00
commit 7017f94e1e
94 changed files with 5950 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

132
.gitattributes vendored Normal file
View File

@@ -0,0 +1,132 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow 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
*.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
*.safetensors 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
pytorch_model-00023-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00022-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00019-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00044-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00020-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00042-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00038-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00039-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00041-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00021-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00040-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00024-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00048-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00055-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00049-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00052-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00043-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00046-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00051-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00045-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00047-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00054-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00050-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00061-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00053-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00056-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00057-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00063-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00062-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00058-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00060-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00064-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00074-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00073-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00067-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00068-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00070-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00071-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00066-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00076-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00059-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00075-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00079-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00077-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00081-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00069-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00080-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00025-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00065-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00078-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00072-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00082-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00030-of-00082.bin filter=lfs diff=lfs merge=lfs -text
tokenizer.model filter=lfs diff=lfs merge=lfs -text
pytorch_model-00026-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00027-of-00082.bin filter=lfs diff=lfs merge=lfs -text
training_args.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00031-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00032-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00005-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00007-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00033-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00029-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00002-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00008-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00001-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00006-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00009-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00037-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00003-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00036-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00035-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00034-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00004-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00012-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00014-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00013-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00011-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00010-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00016-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00015-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00017-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00018-of-00082.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00028-of-00082.bin filter=lfs diff=lfs merge=lfs -text

60
README.md Normal file
View File

@@ -0,0 +1,60 @@
This is a llama-13B based model. (sorry, I forgot to put it in the model name)
Base Model: GPT4-x-Alpaca full fine tune by Chavinlo -> https://huggingface.co/chavinlo/gpt4-x-alpaca
LORA fine tune using the Roleplay Instruct from GPT4 generated dataset -> https://github.com/teknium1/GPTeacher/tree/main/Roleplay
LORA Adapter Only: https://huggingface.co/ZeusLabs/gpt4-x-alpaca-rp-lora/tree/main/gpt-rp-instruct-1
Merged LORA to the model.
FYI Latest HF Transformers generates BROKEN generations.
Try this instead if your generations are terrible (first uninstall transformers): pip install git+https://github.com/huggingface/transformers@9eae4aa57650c1dbe1becd4e0979f6ad1e572ac0
Instruct it same way as alpaca / gpt4xalpaca:
```
### Instruction:
<prompt>
### Response:
```
or
```
### Instruction:
<prompt>
### Input:
<specific data to manipulate for the instruction
### Response:
```
For a better idea of prompting it for roleplay, check out the roleplay discord bot code I made here: https://github.com/teknium1/alpaca-roleplay-discordbot
Here is an example:
```
### Instruction:
Role play as character that is described in the following lines. You always stay in character.
{"Your name is " + name + "." if name else ""}
{"Your backstory and history are: " + background if background else ""}
{"Your personality is: " + personality if personality else ""}
{"Your current circumstances and situation are: " + circumstances if circumstances else ""}
{"Your common greetings are: " + common_greeting if common_greeting else ""}
Remember, you always stay on character. You are the character described above.
{past_dialogue_formatted}
{chat_history if chat_history else "Chatbot: Hello!"}
Always speak with new and unique messages that haven't been said in the chat history.
Respond to this message as your character would:
### Input:
{text}
### Response:
{name}:
```
---
tags:
- llama
- alpaca
- gpt4
---

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": "./gpt4-x-alpaca/",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"pad_token_id": -1,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.27.0.dev0",
"use_cache": true,
"vocab_size": 32001
}

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": 0,
"eos_token_id": 1,
"pad_token_id": 0,
"transformers_version": "4.27.0.dev0"
}

3
pytorch_model-00001-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:68d40e3d745af92c526aadb303dcc07f1eefdbcef1a9f218842b61b3696e1f10
size 380120315

3
pytorch_model-00002-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47844f9ea2d2e3a3270e0366d4b031067bba31fdb0f8d6bc58b5ee7dc86b2d91
size 298846638

3
pytorch_model-00003-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac623fabb64faa06b7f4cdb129ead6d5d0d1bddaedf5fa7614e97c5b0ee2839d
size 387996095

3
pytorch_model-00004-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd9eaca3f678a80c5d2dc90cc12ec3008fa5437fa13b5cd1196c9598e3daeaff
size 387975598

3
pytorch_model-00005-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c7899289297d73ef6829218f522ce9ecd737113d44772636a85fc7d32bbf52b8
size 351296801

3
pytorch_model-00006-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:59f29b287fe55c11181d94e6f7482f1ff21cb029d1fe15df7bf3390a5ec1cd75
size 283116795

3
pytorch_model-00007-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:728ddf7d379775e59e7ecb4003ce51281c116ac5ac47fac6adbd42e102a9963b
size 351296801

3
pytorch_model-00008-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:493a72db0e07051428ffad790ef66a5df0eea30f64d1d33fb6a7cd03837b6f16
size 283116795

3
pytorch_model-00009-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:faa8a4c3fec7ca0cb3cd388e3b9986bc7c27f76d7781727ef7b32ea757197b7a
size 351296801

3
pytorch_model-00010-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7880df8cac8a85884c201dc74ba1aec4033d65f2d303ca6a8ce84f6c879d997f
size 283116795

3
pytorch_model-00011-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c1f2aef611771e6945c87f246853c75be8b811515d33b298885ff3f3fa3e597
size 351296801

3
pytorch_model-00012-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b71da7d88220eab19a65467ab2e7bcc5a7540eb886a75ae2c0cb435981d643d3
size 283116795

3
pytorch_model-00013-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:73106eb1439912b019cd41e36b29c93323a85341a3edd0be7e44ce7ec636b002
size 351296801

3
pytorch_model-00014-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37c66606b85d6ae991b5c8cc288e64d37ea6e1933cd559a631b6eb31e61f1c0e
size 283116795

3
pytorch_model-00015-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d1f689e8cb63989bee9b14f541a6ff0d6609b05b5f20faa8a2173efb705b70d
size 351296801

3
pytorch_model-00016-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7d3f0ce6c6cb314c0f76087c4310c9033d2b0f76ff0e93d9bfdfb5ff11a3ace2
size 283116795

3
pytorch_model-00017-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:003a989eb254cb289cc02054abf26389d6c27e3c61c9fea68795ab79009bec4b
size 351296801

3
pytorch_model-00018-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f60c7da489748e41c59cdaefd367a34e041ffedc1f8d6237c345ed066d9233f2
size 283116795

3
pytorch_model-00019-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bbe020bfb2cba772b8a1b7748ad881c1b6ec7e87a71a88c84c2338f8c407941e
size 351296801

3
pytorch_model-00020-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4342abfb07166124bebf76fc29c9cd31144d0d558baab6641e1438586eefcb84
size 283116795

3
pytorch_model-00021-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f5600074ec967f706dd4e16da360dab25e220f672474286a1c40a0933833f1e4
size 351296865

3
pytorch_model-00022-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:937fff7265785ba9f028d119c704b2d67673e021ac4e71a5dcef25683656d0e5
size 283116795

3
pytorch_model-00023-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c7a3a2d512d576fd2514022ffa46d1cb37f87edfbba54bcbea77513ea4e9200
size 351296865

3
pytorch_model-00024-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:750b3fa510a0a8c88b9f0bc9359fc389365f287610d666838e0a1a9a88a09a89
size 283116795

3
pytorch_model-00025-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa2c42685c2c3e3861f93147683b04ccfdf85e254335378e4aca8ef5a1f4d95e
size 351296865

3
pytorch_model-00026-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f7eab05dc58753189c95db47ee3b7fd3d61bb502c61906fea5c2a53f66c1265
size 283116795

3
pytorch_model-00027-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1aea7410ecfd7572d227b026d953b0bad360f1f787ef1a28eda85d5df9451a5
size 351296865

3
pytorch_model-00028-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54d297089fe3775c512d656e591df7fc48545dede417b28449e40271220a1bfc
size 283116795

3
pytorch_model-00029-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eedc665af44613b2cb2b5e0dc82e24de8d2dbba135f6cd2eb65dfee033590676
size 351296865

3
pytorch_model-00030-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2c10b45a37b14b10e4c63dd9788a7a6c9c1982c2de26a8280576ea0207103eb
size 283116795

3
pytorch_model-00031-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7800556b7eb414324b2bbbb0a60a3e7e1a81de7724935ac847abf0c5404ebac1
size 351296865

3
pytorch_model-00032-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:80f019a690caed250ea3abb13403cfcc4487bbd75b04a705a5c95fca71ab43c1
size 283116795

3
pytorch_model-00033-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f424730ab7e28ab2753d155a0d941e4f07ba6917fdb12c1e1be4b243663f65dc
size 351296865

3
pytorch_model-00034-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0fd85a2528ea5c8c6adf8e2b3fd4461b19a8f2119e28d9dc5a82e75acd4c938
size 283116795

3
pytorch_model-00035-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24a00a872970e0cfafda8f01478f91ca820e0eb0ff6ceb07ca5151ed41d826c7
size 351296865

3
pytorch_model-00036-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8dfb93d9d514600aebdf5bc19b98417335ad8f36133c1a69c90c151f80e07a86
size 283116795

3
pytorch_model-00037-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1bd67fe4fb1344f39ad5be3d5145a424eb39d8c26b18b49be64e428cfebe1ce4
size 351296865

3
pytorch_model-00038-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:887a9a59959306b34e2a5b296924da1924ecaef721e5607e0fedd440227365e2
size 283116795

3
pytorch_model-00039-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dfb7b2e5bcfe6c3ced0d8fa388155b3ccbb97dd540c8cfb05eaf82f34448fda7
size 351296865

3
pytorch_model-00040-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74a97e7efd42e8f367c6bb57f8567d5ed945e553ad3060f08cdb1103d962197d
size 283116795

3
pytorch_model-00041-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d6ac10997ce3e038359406501c8806c5676b651f26df226c7ed9f35a8f2c9061
size 351296865

3
pytorch_model-00042-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b734573bc7df85a70f56af0b1408d6a51bc3dd388b26d6de8be766188484023f
size 283116795

3
pytorch_model-00043-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2aceb85212e96cd1488031855cd34dce9049163f6574422b691dcfffda004dbe
size 351296865

3
pytorch_model-00044-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:593fe18b227517554d4089379492d634f2b3fc757f11deb42eff2790990d4dc4
size 283116795

3
pytorch_model-00045-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d4f2cff79a69f1a7cbc3f50c2b747ff9bca3ee7560e01d53d89fb233acdd1f53
size 351296865

3
pytorch_model-00046-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bdfbdfef83a1177daa420679ccac0c3de8bf53d0ac276a58150fe0ee26888078
size 283116795

3
pytorch_model-00047-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2f1f1bed8e3467c9b316d8c4171d072ea32869d2245cd80e92cfebeeba2b146
size 351296865

3
pytorch_model-00048-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce018860d6d4bc40344e8b4456918d535dbaba99d23ce62c8cb29e609ddbe594
size 283116795

3
pytorch_model-00049-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6769009413c22bc8a1e7c9c8fead4f267b98768d68a56d86958bee120a03196e
size 351296865

3
pytorch_model-00050-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:915cfe76125cb65887dbc987f8e76cbaf31704b98efe94d83d29af0fd37dc56c
size 283116795

3
pytorch_model-00051-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5b9881912273206d2f5f9bedf1b53c42c9f3d3e85dd1fda4a8f38974c2235c8
size 351296865

3
pytorch_model-00052-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30b8b6cbc9cf3c86340ad1a0f5ec9982f5b22b89b88bc7e1dd9324bd15e214f7
size 283116795

3
pytorch_model-00053-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78620cddbd44c40422196d0889c011735e59b9c7f2d2307dbf5f757f4a95c0e9
size 351296865

3
pytorch_model-00054-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbba8eb8117289a65247415c5cb80c844bb3073653a81f2da609c4a69ca408a3
size 283116795

3
pytorch_model-00055-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d4af88aed72e4c38a92c786e39c5fb9c7583e2e33259904fcc959d8096d1a4c0
size 351296865

3
pytorch_model-00056-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b51d868412e3ddb41bcff8eda3286fea7e540334ce67ce9e18a3b2fadd77bc8
size 283116795

3
pytorch_model-00057-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08d9ec9bb5b228dc4cb1b0f383908e2260805cc8c035ab0b654026fe5d98b8f9
size 351296865

3
pytorch_model-00058-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8da14d3f915b7294592d2ffda939335a0695db13aebb26093c477a9e9f2889dd
size 283116795

3
pytorch_model-00059-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ae512193cb01b89343d6f5ac0bd3a741bf5e3595eaf8aba38198b50ca07025ab
size 351296865

3
pytorch_model-00060-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:af986bbba51c998f231eea3f0f5db1721ff0b82d1acc9eee50365dd616ce0955
size 283116795

3
pytorch_model-00061-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02d7ce585f1d942f912c65c392259f0bc2a3c2c96d9bed933b6036562f225a5c
size 351296865

3
pytorch_model-00062-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fc4075b05e87595a58c509358ec4dbcc45db86a8c5d5710f75a0cd2353182ec1
size 283116795

3
pytorch_model-00063-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f7006505f13559aa1d2e2971a61e7a73bdc81b2eb598a1444a98dceaec7ed2d3
size 351296865

3
pytorch_model-00064-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3ad7da460437e0909920b0744cf078ba0b4381c65d831816a804edafeb432c3
size 283116795

3
pytorch_model-00065-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:39ef521bba8f7fb3ef0b546eb94e33a4537628bbb5ada8eb137f60471c452a54
size 351296865

3
pytorch_model-00066-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:91cfa6c35a06c1ff77a8a2fd55c3e697188bbeb83204fc51dd5305035de921aa
size 283116795

3
pytorch_model-00067-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e006a5d0b381af501d34121f1dd5ce6bec9dc98a3673ddc2981d0e9e1c048ff6
size 351296865

3
pytorch_model-00068-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d72f83e1ca852aed206b6959d74052b51545692a42531d3f25169f05b07b77a7
size 283116795

3
pytorch_model-00069-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f759b2e924a6ee2881ba1b12321b012ade425557cb89ea6a7c72862d4f722a8
size 351296865

3
pytorch_model-00070-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e6d9b2fc706c193b60cd700fb913ba1753b9bbae3596e46019cec1238fbac81
size 283116795

3
pytorch_model-00071-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:57e26fb2db5c93c0e6abddf80396a4ba55a31762d666d817d18c507e30205710
size 351296865

3
pytorch_model-00072-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1174da5c737096c2e24469cbad1a1921fd1790e703aa5a7c36f888044d2fb6c
size 283116795

3
pytorch_model-00073-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d7890104a70913ca2d485f65acc6ea189b8d7a7e903df300a0c4428ca895e2b
size 351296865

3
pytorch_model-00074-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d09aed3c3179593fbc0e4a8ed93ebd19c4eff7097f43277dff51ab121b57e597
size 283116795

3
pytorch_model-00075-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27129708d38900a5556d1b3c354220994a4b3972e3101dde87365401f5460c28
size 351296865

3
pytorch_model-00076-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9157443a6806c14b8c6b2d9def534dae0f9536ed3f4dec6144db236a842ba767
size 283116795

3
pytorch_model-00077-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8228c361281be34582f00fe1d6a10e1ba936a8d383765930167ffd3be6b61174
size 351296865

3
pytorch_model-00078-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ceb85814b989834dc762927b2f75ad6a09c87e19d06e90a878ecaf646faba07
size 283116795

3
pytorch_model-00079-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74ba7ff8ab144ba3a8b493799543da500be1c2edd15cd1dd919cb194b2493d65
size 351296865

3
pytorch_model-00080-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22da56777a8465ce5a3d83f17817d38241e43456c5db8da1b6da7ee01f8b1580
size 283116795

3
pytorch_model-00081-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6ce239ca877b2a07c9ffc4dd48902d164335e13f4bdb322b440211dd8859f884
size 141590301

3
pytorch_model-00082-of-00082.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c83b2314ab98ddfcb8f38138b1aa9de3a4dbdbe00e4ea8476c56c896cf25802
size 327691178

410
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,410 @@
{
"metadata": {
"total_size": 26031759360
},
"weight_map": {
"lm_head.weight": "pytorch_model-00082-of-00082.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00082.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00082.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00082.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00082.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00003-of-00082.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00082.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00082.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00082.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00082.bin",
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00082.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00082.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00005-of-00082.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00082.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00004-of-00082.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00005-of-00082.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00005-of-00082.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00082.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00004-of-00082.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00082.bin",
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00082.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00082.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00023-of-00082.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00022-of-00082.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00022-of-00082.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00023-of-00082.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00023-of-00082.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00021-of-00082.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00021-of-00082.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00021-of-00082.bin",
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00082.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00021-of-00082.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00025-of-00082.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00024-of-00082.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00024-of-00082.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00025-of-00082.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00025-of-00082.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00023-of-00082.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00023-of-00082.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00023-of-00082.bin",
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00082.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00023-of-00082.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00027-of-00082.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00026-of-00082.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00026-of-00082.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00027-of-00082.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00027-of-00082.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00025-of-00082.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00025-of-00082.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00025-of-00082.bin",
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00082.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00025-of-00082.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00029-of-00082.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00028-of-00082.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00028-of-00082.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00029-of-00082.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00029-of-00082.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00027-of-00082.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00027-of-00082.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00027-of-00082.bin",
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00082.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00027-of-00082.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00031-of-00082.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00030-of-00082.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00030-of-00082.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00031-of-00082.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00031-of-00082.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00029-of-00082.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00029-of-00082.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00029-of-00082.bin",
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00082.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00029-of-00082.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00033-of-00082.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00032-of-00082.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00032-of-00082.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00033-of-00082.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00033-of-00082.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00031-of-00082.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00031-of-00082.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00031-of-00082.bin",
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00082.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00031-of-00082.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00035-of-00082.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00034-of-00082.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00034-of-00082.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00035-of-00082.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00035-of-00082.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00033-of-00082.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00033-of-00082.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00033-of-00082.bin",
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00082.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00033-of-00082.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00037-of-00082.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00036-of-00082.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00036-of-00082.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00037-of-00082.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00037-of-00082.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00035-of-00082.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00035-of-00082.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00035-of-00082.bin",
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00082.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00035-of-00082.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00039-of-00082.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00038-of-00082.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00038-of-00082.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00039-of-00082.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00039-of-00082.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00037-of-00082.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00037-of-00082.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00037-of-00082.bin",
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00037-of-00082.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00037-of-00082.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00041-of-00082.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00040-of-00082.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00040-of-00082.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00041-of-00082.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00041-of-00082.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00039-of-00082.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00039-of-00082.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00039-of-00082.bin",
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00082.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00039-of-00082.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00007-of-00082.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00006-of-00082.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00006-of-00082.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00007-of-00082.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00007-of-00082.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00005-of-00082.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00005-of-00082.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00005-of-00082.bin",
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00082.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00005-of-00082.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00043-of-00082.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00042-of-00082.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00042-of-00082.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00043-of-00082.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00043-of-00082.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00041-of-00082.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00041-of-00082.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00041-of-00082.bin",
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00041-of-00082.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00041-of-00082.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00045-of-00082.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00044-of-00082.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00044-of-00082.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00045-of-00082.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00045-of-00082.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00043-of-00082.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00043-of-00082.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00043-of-00082.bin",
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00043-of-00082.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00043-of-00082.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00047-of-00082.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00046-of-00082.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00046-of-00082.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00047-of-00082.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00047-of-00082.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00045-of-00082.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00045-of-00082.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00045-of-00082.bin",
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00045-of-00082.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00045-of-00082.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00049-of-00082.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00048-of-00082.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00048-of-00082.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00049-of-00082.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00049-of-00082.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00047-of-00082.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00047-of-00082.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00047-of-00082.bin",
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00047-of-00082.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00047-of-00082.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00051-of-00082.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00050-of-00082.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00050-of-00082.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00051-of-00082.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00051-of-00082.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00049-of-00082.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00049-of-00082.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00049-of-00082.bin",
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00049-of-00082.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00049-of-00082.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00053-of-00082.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00052-of-00082.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00052-of-00082.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00053-of-00082.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00053-of-00082.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00051-of-00082.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00051-of-00082.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00051-of-00082.bin",
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00051-of-00082.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00051-of-00082.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00055-of-00082.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00054-of-00082.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00054-of-00082.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00055-of-00082.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00055-of-00082.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00053-of-00082.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00053-of-00082.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00053-of-00082.bin",
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00053-of-00082.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00053-of-00082.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00057-of-00082.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00056-of-00082.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00056-of-00082.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00057-of-00082.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00057-of-00082.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00055-of-00082.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00055-of-00082.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00055-of-00082.bin",
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00055-of-00082.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00055-of-00082.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00059-of-00082.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00058-of-00082.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00058-of-00082.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00059-of-00082.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00059-of-00082.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00057-of-00082.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00057-of-00082.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00057-of-00082.bin",
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00057-of-00082.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00057-of-00082.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00061-of-00082.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00060-of-00082.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00060-of-00082.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00061-of-00082.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00061-of-00082.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00059-of-00082.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00059-of-00082.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00059-of-00082.bin",
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00059-of-00082.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00059-of-00082.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00009-of-00082.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00008-of-00082.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00008-of-00082.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00009-of-00082.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00009-of-00082.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00007-of-00082.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00007-of-00082.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00007-of-00082.bin",
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00082.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00007-of-00082.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00063-of-00082.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00062-of-00082.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00062-of-00082.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00063-of-00082.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00063-of-00082.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00061-of-00082.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00061-of-00082.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00061-of-00082.bin",
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00061-of-00082.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00061-of-00082.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00065-of-00082.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00064-of-00082.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00064-of-00082.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00065-of-00082.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00065-of-00082.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00063-of-00082.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00063-of-00082.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00063-of-00082.bin",
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00063-of-00082.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00063-of-00082.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00067-of-00082.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00066-of-00082.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00066-of-00082.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00067-of-00082.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00067-of-00082.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00065-of-00082.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00065-of-00082.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00065-of-00082.bin",
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00065-of-00082.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00065-of-00082.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00069-of-00082.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00068-of-00082.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00068-of-00082.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00069-of-00082.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00069-of-00082.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00067-of-00082.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00067-of-00082.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00067-of-00082.bin",
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00067-of-00082.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00067-of-00082.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00071-of-00082.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00070-of-00082.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00070-of-00082.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00071-of-00082.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00071-of-00082.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00069-of-00082.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00069-of-00082.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00069-of-00082.bin",
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00069-of-00082.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00069-of-00082.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00073-of-00082.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00072-of-00082.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00072-of-00082.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00073-of-00082.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00073-of-00082.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00071-of-00082.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00071-of-00082.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00071-of-00082.bin",
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00071-of-00082.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00071-of-00082.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00075-of-00082.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00074-of-00082.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00074-of-00082.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00075-of-00082.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00075-of-00082.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00073-of-00082.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00073-of-00082.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00073-of-00082.bin",
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00073-of-00082.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00073-of-00082.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00077-of-00082.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00076-of-00082.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00076-of-00082.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00077-of-00082.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00077-of-00082.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00075-of-00082.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00075-of-00082.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00075-of-00082.bin",
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00075-of-00082.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00075-of-00082.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00079-of-00082.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00078-of-00082.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00078-of-00082.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00079-of-00082.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00079-of-00082.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00077-of-00082.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00077-of-00082.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00077-of-00082.bin",
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00077-of-00082.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00077-of-00082.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00081-of-00082.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00080-of-00082.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00080-of-00082.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00081-of-00082.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00081-of-00082.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00079-of-00082.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00079-of-00082.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00079-of-00082.bin",
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00079-of-00082.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00079-of-00082.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00011-of-00082.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00010-of-00082.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00010-of-00082.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00011-of-00082.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00011-of-00082.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00009-of-00082.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00009-of-00082.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00009-of-00082.bin",
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00082.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00009-of-00082.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00013-of-00082.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00012-of-00082.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00012-of-00082.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00013-of-00082.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00013-of-00082.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00011-of-00082.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00011-of-00082.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00011-of-00082.bin",
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00082.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00011-of-00082.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00015-of-00082.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00014-of-00082.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00014-of-00082.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00015-of-00082.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00015-of-00082.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00013-of-00082.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00013-of-00082.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00013-of-00082.bin",
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00082.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00013-of-00082.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00017-of-00082.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00016-of-00082.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00016-of-00082.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00017-of-00082.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00017-of-00082.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00015-of-00082.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00015-of-00082.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00015-of-00082.bin",
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00082.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00015-of-00082.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00019-of-00082.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00018-of-00082.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00018-of-00082.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00019-of-00082.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00019-of-00082.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00017-of-00082.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00017-of-00082.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00017-of-00082.bin",
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00082.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00017-of-00082.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00021-of-00082.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00020-of-00082.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00020-of-00082.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00021-of-00082.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00021-of-00082.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00019-of-00082.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00019-of-00082.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00019-of-00082.bin",
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00082.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00019-of-00082.bin",
"model.norm.weight": "pytorch_model-00081-of-00082.bin"
}
}

6
special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "</s>",
"eos_token": "</s>",
"pad_token": "[PAD]",
"unk_token": "</s>"
}

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

Binary file not shown.

9
tokenizer_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"bos_token": "",
"eos_token": "",
"model_max_length": 2048,
"padding_side": "right",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--decapoda-research--llama-13b-hf/snapshots/438770a656712a5072229b62256521845d4de5ce/special_tokens_map.json",
"tokenizer_class": "LlamaTokenizer",
"unk_token": ""
}

5047
trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:93499e6d2b72f466e8db31be3266bf88f883698f46eeef49a084987dc0e7e0de
size 3707