chainyo
commited on
Commit
·
cbbe0bc
1
Parent(s):
d6ded8c
add model weights
Browse files- README.md +20 -0
- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00039.bin +3 -0
- pytorch_model-00002-of-00039.bin +3 -0
- pytorch_model-00003-of-00039.bin +3 -0
- pytorch_model-00004-of-00039.bin +3 -0
- pytorch_model-00005-of-00039.bin +3 -0
- pytorch_model-00006-of-00039.bin +3 -0
- pytorch_model-00007-of-00039.bin +3 -0
- pytorch_model-00008-of-00039.bin +3 -0
- pytorch_model-00009-of-00039.bin +3 -0
- pytorch_model-00010-of-00039.bin +3 -0
- pytorch_model-00011-of-00039.bin +3 -0
- pytorch_model-00012-of-00039.bin +3 -0
- pytorch_model-00013-of-00039.bin +3 -0
- pytorch_model-00014-of-00039.bin +3 -0
- pytorch_model-00015-of-00039.bin +3 -0
- pytorch_model-00016-of-00039.bin +3 -0
- pytorch_model-00017-of-00039.bin +3 -0
- pytorch_model-00018-of-00039.bin +3 -0
- pytorch_model-00019-of-00039.bin +3 -0
- pytorch_model-00020-of-00039.bin +3 -0
- pytorch_model-00021-of-00039.bin +3 -0
- pytorch_model-00022-of-00039.bin +3 -0
- pytorch_model-00023-of-00039.bin +3 -0
- pytorch_model-00024-of-00039.bin +3 -0
- pytorch_model-00025-of-00039.bin +3 -0
- pytorch_model-00026-of-00039.bin +3 -0
- pytorch_model-00027-of-00039.bin +3 -0
- pytorch_model-00028-of-00039.bin +3 -0
- pytorch_model-00029-of-00039.bin +3 -0
- pytorch_model-00030-of-00039.bin +3 -0
- pytorch_model-00031-of-00039.bin +3 -0
- pytorch_model-00032-of-00039.bin +3 -0
- pytorch_model-00033-of-00039.bin +3 -0
- pytorch_model-00034-of-00039.bin +3 -0
- pytorch_model-00035-of-00039.bin +3 -0
- pytorch_model-00036-of-00039.bin +3 -0
- pytorch_model-00037-of-00039.bin +3 -0
- pytorch_model-00038-of-00039.bin +3 -0
- pytorch_model-00039-of-00039.bin +3 -0
- pytorch_model.bin.index.json +330 -0
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Alpaca LoRa 7B
|
| 2 |
+
|
| 3 |
+
This repository contains a LLaMA-7B fine-tuned model on the [Standford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) cleaned version dataset.
|
| 4 |
+
|
| 5 |
+
I used [LLaMA-7B-hf](decapoda-research/llama-7b-hf) as a base model
|
| 6 |
+
|
| 7 |
+
# Usage
|
| 8 |
+
|
| 9 |
+
## Using the model
|
| 10 |
+
|
| 11 |
+
```python
|
| 12 |
+
from transformers import LlamaTokenizer, LlamaForCausalLM,
|
| 13 |
+
|
| 14 |
+
tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/alpaca-lora-7b")
|
| 15 |
+
model = LlamaForCausalLM.from_pretrained(
|
| 16 |
+
"chainyo/alpaca-lora-7b",
|
| 17 |
+
load_in_8bit=True,
|
| 18 |
+
torch_dtype=torch.float16,
|
| 19 |
+
device_map="auto",
|
| 20 |
+
)
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 1,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_sequence_length": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"pad_token_id": -1,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"torch_dtype": "float16",
|
| 20 |
+
"transformers_version": "4.28.0.dev0",
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"vocab_size": 32000
|
| 23 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0.dev0"
|
| 7 |
+
}
|
pytorch_model-00001-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6d643b042185fc9a594be1fc68d6cf28e7c4066e77faf35e2e32968ab9640fe
|
| 3 |
+
size 396364479
|
pytorch_model-00002-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0ed40da66089a977c250d7e8a3d7fb6939f369c75986fad0aa0e72cc1c1f610
|
| 3 |
+
size 371215393
|
pytorch_model-00003-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b0989d7cb39aca231afcff32cbcab29327cc9c45b3d8ec006391571ff2c9949
|
| 3 |
+
size 371215986
|
pytorch_model-00004-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:023abb6adea627df974e693778f82bcf8da839678a496f8c3a2e308bba2b5eaa
|
| 3 |
+
size 371215986
|
pytorch_model-00005-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97490b8826e471d3f9286fbfe0551ab8c39f7c14729792d1f999221ebd495294
|
| 3 |
+
size 371215986
|
pytorch_model-00006-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc0ac91d6f83699efd72e527a7e48e6f7f997e2807ff5b537a13783864d15bf5
|
| 3 |
+
size 314575888
|
pytorch_model-00007-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ceaf76a78fefbd8937c2342e09d3ad37a1f0f7257f9b7698e2f9d0579b180e2f
|
| 3 |
+
size 314592882
|
pytorch_model-00008-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b822e54cca11c7dffbb5c5bc3e864afeff8c26a19d75da35802127e58efc2b74
|
| 3 |
+
size 314592882
|
pytorch_model-00009-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1158dca80b45679d989baee30469c1eb5a728c1d27efbafd41d5791afd929ecd
|
| 3 |
+
size 371215393
|
pytorch_model-00010-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad808f8aa6157a7f218466b5fb6a712ec0869aeba8f1913d302205ef84c41517
|
| 3 |
+
size 371215986
|
pytorch_model-00011-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1730e511925d15b9dc43a5d224e46142fa48430182cfea3b0e055353c26d9acd
|
| 3 |
+
size 371215986
|
pytorch_model-00012-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed49d27e7392e8c695db256c9edacbe5fec2e30f613e91f9f9a34881f9f14e2e
|
| 3 |
+
size 371215986
|
pytorch_model-00013-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c634fe5358313e99f110bcdc2d2eca4193456f393849157bdda034f343e44bd
|
| 3 |
+
size 314575888
|
pytorch_model-00014-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa18c41f5d4c3dd3102601ff438b2032adfcb970f7c73589bdd80edf3a8d15ba
|
| 3 |
+
size 314592882
|
pytorch_model-00015-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ea3fa408d8d15e7f63866caf8d726895f5b572576caa8fb7fbbb513724355c3
|
| 3 |
+
size 314592882
|
pytorch_model-00016-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:411890749b8ce0783b8197eb7e4968f8a49ed4619a93a7453641c1a7106ddf59
|
| 3 |
+
size 371215393
|
pytorch_model-00017-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab871faecd52b6f8b7cbafc577e2a059db5ec1fbd8ab8b5ef5da6a2ceffd5a5e
|
| 3 |
+
size 371215986
|
pytorch_model-00018-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19b7cd10832736214705d9eb2675b9b1667cd8d3c5fe107f1df85c649fbfa16a
|
| 3 |
+
size 371215986
|
pytorch_model-00019-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c4729335ed1226347a32477333cec4a85e0be6ec535ebf019e3c59c34b8e88
|
| 3 |
+
size 371215986
|
pytorch_model-00020-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfae9635bb7c9ade7ad218f886ed7f7007fc923d219dd40eedd6db36e43aaba0
|
| 3 |
+
size 314575888
|
pytorch_model-00021-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3deb7dbc21695274e1641c82c9134666ed9630044b48eb18453701118989e57b
|
| 3 |
+
size 314592882
|
pytorch_model-00022-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:202d7ce7a775b273cc9badd35a075a68ac85abb0c207d71627f8c9ac80593e83
|
| 3 |
+
size 314592882
|
pytorch_model-00023-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ce200b7acec4d97dc935cc5c3d3bd675f1106293fe3a431a4db011a55e79707
|
| 3 |
+
size 371215393
|
pytorch_model-00024-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32fd7a47923af58e16eeac3cd30522e2d996b0b8b5e1a679218740b4ca7c560c
|
| 3 |
+
size 371215986
|
pytorch_model-00025-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3231fe826a54070bc50bc079411ce3e053f2754cfc1df99d81636a1e65f2e96d
|
| 3 |
+
size 371215986
|
pytorch_model-00026-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5f327d3225017f9a76a709ea5f3cfd8a7ac31201fa982a91e656abe79c681a9
|
| 3 |
+
size 371215986
|
pytorch_model-00027-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13e36fad51e0ed450a26f6a0df0e5a54da36cc9b11880fa1e6cb78f547523c2f
|
| 3 |
+
size 314575888
|
pytorch_model-00028-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70bdade42999a45556acbc59f84e243c914727ff3a0df21def1aec910c8a1a63
|
| 3 |
+
size 314592882
|
pytorch_model-00029-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:309a55d4438eeb420fe55d0d5f2f839b2a57a70b5319b9c52944e6820d152907
|
| 3 |
+
size 314592882
|
pytorch_model-00030-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2140a18cc1022babc308c1dfafe9a3703536f4aa941e6b0b4fab5d0f7ef396c9
|
| 3 |
+
size 371215393
|
pytorch_model-00031-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c37701696a1dd25937001b8c155581f56c0448db200a20bd41bcb769702cf6bb
|
| 3 |
+
size 371215986
|
pytorch_model-00032-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1da7fdd75386dcb49549fe47512cfe121bc1e1b35288009d02ab86563810d48d
|
| 3 |
+
size 371215986
|
pytorch_model-00033-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d764c98487c12227781ddc2d03abc1f958cdf9c524b7e453f83d15d31b26410
|
| 3 |
+
size 371215986
|
pytorch_model-00034-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a507e79cc1a1f3051b30811b370c386869c2daf283ff06dbcba6413ee2882722
|
| 3 |
+
size 314575888
|
pytorch_model-00035-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:334c947fae96c0a2276fb2d31793a65587df1d5f61b3630a3dfe7a775a7cfd1d
|
| 3 |
+
size 314592882
|
pytorch_model-00036-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fb6b4edf40d19fc271b621de8e29d3411365f963e44f9cc8ad61f00a12b76c5
|
| 3 |
+
size 314592882
|
pytorch_model-00037-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52e53bf5779a24d9f7c9a73cf0e57f5b1bcb0a52c200ddb51f7e55bc76736107
|
| 3 |
+
size 371215393
|
pytorch_model-00038-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6762c675eb30868665ce8ada7a2bbbd117e02f44d47ba3c8dcf91f5623e5ce67
|
| 3 |
+
size 304114977
|
pytorch_model-00039-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3350fb71c2bc1e88d77d9685716fd2759e879137814a4120d98265a43f405919
|
| 3 |
+
size 262144938
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476839424
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00039-of-00039.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 328 |
+
"model.norm.weight": "pytorch_model-00038-of-00039.bin"
|
| 329 |
+
}
|
| 330 |
+
}
|