Model added.
Browse files- config.json +27 -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
- tokenizer.model +3 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "0mij/llama-7b-webnlg-full",
|
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_position_embeddings": 2048,
|
13 |
+
"max_sequence_length": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 32,
|
18 |
+
"pad_token_id": -1,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.31.0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
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": "4.31.0"
|
7 |
+
}
|
pytorch_model-00001-of-00039.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1cb1d9d94bceddcf1e3cb4be13f1d127d2b12b7a8246e8aa4b714af8d09c988
|
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 sha256:11e0798f2b4de191f5ec254c02f052e360d106a23b02d3b88543f566e4b5aeab
|
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:e6e2e59410379d7a1ef572b3e5523d2fcaba43c30b68b20a0906e272a71c96a0
|
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:cab543af74dac6390055d87c5fa38775d55dcaf3c67338c5471ef5bc1725a100
|
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 sha256:05cb01aa3ffbe8a39f322aa7f00084ddf0beb93b1d9e08cab9b3337fbe01e0c9
|
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 sha256:1ecc0f6b00c71e121acfa4283825d76d5853acc428af7481c724335451202af2
|
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 sha256:7655510f00dc53c4671e149547ab346c5f382ecf2229857de614771f4395c82c
|
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 sha256:3e67c177c58c5623c23485a142fce66160ae1d55c1d6bc06d3a242f3b772c1e7
|
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 sha256:5e9943fe747b4541da4c25125e18aa32d9bf794a26a112d8bfb7f9b2d2a56d5b
|
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:e5917cd7e2b4c9d4778af2a0fb198c90718eb5de740089d2ffefbcfc8e920453
|
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:e58964c593d9bd12e40f5dc28163ae3c4e61f6bc52c56e3bd854392fc73c7d09
|
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 sha256:715d6972a0a68973cd0b1fb757d33119a90dc23f09204965b001a0f81bb251ff
|
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 sha256:609abe9719d38d5927515fb9d8595ec3bfd1deb631df6fbe08cea7e0e8374ae7
|
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 sha256:3b89188d8022a1418756b7d1d5a16c1190b7460d1b9a3a22ec1186ef1d6aefd1
|
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 sha256:1e34730606ab3f7636cc30db09845e352a844a0c4c8d0099afd4967862078a66
|
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 sha256:50725daa8e5e83a204a10c26868d35cedc3344433d6ae31789dc26c91e43a339
|
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:d9aca3160ac33d8ac63ee7d9380b8e86c9fa4d30b4f96407dd747a9816a4320f
|
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 sha256:0cf112c65aa7a35260cef79486e467d4516c5dd11ec856c13081119adff8ddc1
|
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:db4cddeb7a72e265178b0fb7f0746df4a07e9cf4be1cc36b53e68a8a6b981a59
|
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 sha256:5aec7e48fb525b8cadfc80968cb63b57ae63d9242104b14b9cdc03d1942d78e6
|
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 sha256:81e68396e64ba263554710204433b7b45f1ab1762c86a7b09c31d8f5990a06b8
|
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 sha256:5b604374e33ae1ab11eee5d8fa73b0c88c608d4d53667fe2e85045205b742a5a
|
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 sha256:622f570d309f20a7cabe07239cc258bb493be4ae70b7e8d663d58540eef4ae6d
|
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:e3a542b711c0ab83c9dfed89f7814f7b20c7a9c1e5f96c2c71ddd3c03834f96d
|
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 sha256:0f9e59aa122b9790006f83371e67bd27100ef9eef0e05edf33411feff439daec
|
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 sha256:1da48fd8d54720abcb5b905f0e794d9cbe478b70be163225aa3b573d749f18d8
|
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 sha256:2f54d6235bd8b0d7d08afe9926cf8cc45ec8bf79f617fe1f5f44c60b8a5f1441
|
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:e70dc410296d2db6e522fb8f54f29b3669d509468ef59838426a16cf7d788da3
|
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 sha256:718b5a32ecda1f19f53e2db626402a80a046315fb38f75b3f6d23573328bf52d
|
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 sha256:49b6ed3bb4e4b277cbf2b8e5953653415dcc1761c7524b6646082260dee72918
|
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 sha256:5165074408f64f2836f9bf3549b494783ca1dcd83657a9829b5b3576e18d63d9
|
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 sha256:73153ec19819238a0bb183a967a9347182188c8ed2b7cd9ea9dd98b83e82dc13
|
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:dd435d88005104f6b2e51aace32c4457e5d970b459a93a2f5c14a1f3864e81f7
|
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 sha256:1ea2b5b95070f6f628a2cf2eec2ba1ec5e7d6c01b1d914b636f25de6fe6b14e5
|
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 sha256:4027c88d08e717e96d84c03ce26feb89aea03a03b42b95baf9672241d6942021
|
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 sha256:08748e2d75b1c0668f64e87611c84f13a29b054f4ecf855ac97d33d0554ff475
|
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:e90a8d64bcdf36f8c3278142e86176b8f76d070f34767059a2a86e5b7be5ad3e
|
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 sha256:05a82e76093ccf5769b4dfa98a93078a1c54e3483dc145a40b380d028badf9a6
|
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-00014-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-00013-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-00021-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-00020-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-00028-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-00027-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-00035-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-00034-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-00007-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-00006-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 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LLaMATokenizer", "unk_token": ""}
|