Upload LlamaForCausalLM
Browse files- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00042.bin +3 -0
- pytorch_model-00002-of-00042.bin +3 -0
- pytorch_model-00003-of-00042.bin +3 -0
- pytorch_model-00004-of-00042.bin +3 -0
- pytorch_model-00005-of-00042.bin +3 -0
- pytorch_model-00006-of-00042.bin +3 -0
- pytorch_model-00007-of-00042.bin +3 -0
- pytorch_model-00008-of-00042.bin +3 -0
- pytorch_model-00009-of-00042.bin +3 -0
- pytorch_model-00010-of-00042.bin +3 -0
- pytorch_model-00011-of-00042.bin +3 -0
- pytorch_model-00012-of-00042.bin +3 -0
- pytorch_model-00013-of-00042.bin +3 -0
- pytorch_model-00014-of-00042.bin +3 -0
- pytorch_model-00015-of-00042.bin +3 -0
- pytorch_model-00016-of-00042.bin +3 -0
- pytorch_model-00017-of-00042.bin +3 -0
- pytorch_model-00018-of-00042.bin +3 -0
- pytorch_model-00019-of-00042.bin +3 -0
- pytorch_model-00020-of-00042.bin +3 -0
- pytorch_model-00021-of-00042.bin +3 -0
- pytorch_model-00022-of-00042.bin +3 -0
- pytorch_model-00023-of-00042.bin +3 -0
- pytorch_model-00024-of-00042.bin +3 -0
- pytorch_model-00025-of-00042.bin +3 -0
- pytorch_model-00026-of-00042.bin +3 -0
- pytorch_model-00027-of-00042.bin +3 -0
- pytorch_model-00028-of-00042.bin +3 -0
- pytorch_model-00029-of-00042.bin +3 -0
- pytorch_model-00030-of-00042.bin +3 -0
- pytorch_model-00031-of-00042.bin +3 -0
- pytorch_model-00032-of-00042.bin +3 -0
- pytorch_model-00033-of-00042.bin +3 -0
- pytorch_model-00034-of-00042.bin +3 -0
- pytorch_model-00035-of-00042.bin +3 -0
- pytorch_model-00036-of-00042.bin +3 -0
- pytorch_model-00037-of-00042.bin +3 -0
- pytorch_model-00038-of-00042.bin +3 -0
- pytorch_model-00039-of-00042.bin +3 -0
- pytorch_model-00040-of-00042.bin +3 -0
- pytorch_model-00041-of-00042.bin +3 -0
- pytorch_model-00042-of-00042.bin +3 -0
- pytorch_model.bin.index.json +410 -0
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sharpbai/open_llama_13b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 13824,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 40,
|
| 15 |
+
"num_hidden_layers": 40,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"torch_dtype": "float16",
|
| 20 |
+
"transformers_version": "4.30.2",
|
| 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": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
pytorch_model-00001-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5121c6e0e517920fa3933570868b61b2ddee66314d93cde875f63d9d38d8cb74
|
| 3 |
+
size 537397951
|
pytorch_model-00002-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c64cad1bc9e5b52da2b3b9e1ea515d6b22b13a72c1596cf555f9945fa52c4e29
|
| 3 |
+
size 634412995
|
pytorch_model-00003-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32cb1d30756b8648ff41b4090fff6bf4911ea241f8b2bd112596dfe63c450b18
|
| 3 |
+
size 634412995
|
pytorch_model-00004-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ace5eecdbba3d7f73ad085a89e89e2d7a99c7ef69e6ed515630e7709a86ec49
|
| 3 |
+
size 634412995
|
pytorch_model-00005-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46ffe240e1ea82415c2a6abec31decef7afafe42d2067426b27d460d5ef6bcd6
|
| 3 |
+
size 634412995
|
pytorch_model-00006-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:024cb4ab1dd9c18cc0b958c1468741f8f73a5b92caa07c42ad47d8e1bd4dd180
|
| 3 |
+
size 634412995
|
pytorch_model-00007-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cb6e6c8e554d86bd707667686fb4c2ee458c116b1064a59adb7fea0f296ca69
|
| 3 |
+
size 634412995
|
pytorch_model-00008-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8f823749b66bc53dc5365047515596045b373eb2704d498493ea41bcc2361d1
|
| 3 |
+
size 634412995
|
pytorch_model-00009-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50f62d8b24fec13c3ce271142c0a033507b773b6a4b52e01dd03116f3154bf1c
|
| 3 |
+
size 634412995
|
pytorch_model-00010-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2774f7ebe32a32c590135ac9c01bdf520c3b2a56a192e1e6674de9202cc0f762
|
| 3 |
+
size 634412995
|
pytorch_model-00011-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca053d89142bac825f2f8b5658d62e594d50ca124538b3da3a918c1ab95a0c61
|
| 3 |
+
size 634412995
|
pytorch_model-00012-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dde1d86c1ba94256af9e4949d5958bc96260115b585249ffa51e7062803b6db2
|
| 3 |
+
size 634412995
|
pytorch_model-00013-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8306b66c908bfe8166c73c3bab2baf3cc50268b18c68c9cf75cef6bc31d4a69
|
| 3 |
+
size 634412995
|
pytorch_model-00014-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6d94b8124cd4def287f4d1618ec4c9c100dfde7cdb19d01b45a444269425f87
|
| 3 |
+
size 634412995
|
pytorch_model-00015-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69c75a547a09073a54ec83e6dcf8b24eff41d7e0d445cfb9c32b833a79bf93a
|
| 3 |
+
size 634412995
|
pytorch_model-00016-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef069df50a7c8f399dc952b5b1891a0336ead497467313d04297cde9f3946ae8
|
| 3 |
+
size 634412995
|
pytorch_model-00017-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18712afd05ed176baa1ba98a8211066cf93ac523f56587e06939c9150d9a70cf
|
| 3 |
+
size 634412995
|
pytorch_model-00018-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51d3e5d0f6455599b73d4a2aff80e0789950ea39bc1e67503b0846b1163219dc
|
| 3 |
+
size 634412995
|
pytorch_model-00019-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a03dae6e0c1a5b72588645cc96897be6c146966d99ef558483471de4679ce53
|
| 3 |
+
size 634412995
|
pytorch_model-00020-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b24c72ab6f9751e77a514a71adbd47c984f5f979fcaa36a72eb4e713940b2dc5
|
| 3 |
+
size 634412995
|
pytorch_model-00021-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23394b59f27b6600ff6abd9b4cdf306541d41d5811db32eda3e562e8ad986dae
|
| 3 |
+
size 634412995
|
pytorch_model-00022-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a36723d6463eb42e6e311d25c1c365b75b589653b266d2a3a7bed7560ac3e571
|
| 3 |
+
size 634412995
|
pytorch_model-00023-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79a6d28424abd5c910d604f1664b41e063a6745633a98c81f34d730eff2ebad1
|
| 3 |
+
size 634412995
|
pytorch_model-00024-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d5d1e8e7f4ad9db3435f6566d2b8f8c0090c977f73f662224980d9b43964cf9
|
| 3 |
+
size 634412995
|
pytorch_model-00025-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:549beee33fe83f1d2d79685908cdc0fa9a84a1644165bfbc5cda02d62223db1f
|
| 3 |
+
size 634412995
|
pytorch_model-00026-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbd4a44982d19d613a34dc2497ea431ed18c067f525e270b0c9bb24935d718d0
|
| 3 |
+
size 634412995
|
pytorch_model-00027-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17a8d9f86e3d1a2a17bc350cc604def5772a8da1c6e7d704cfa371f098f1f960
|
| 3 |
+
size 634412995
|
pytorch_model-00028-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0a9345ac6bdd5c7adcbd121a00f0e6b34a29dd95151cd0880346257f0b2e9f8
|
| 3 |
+
size 634412995
|
pytorch_model-00029-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ff4927c745b32b60874582afb7d7672226365d795aed36afb90b5c8c3505e98
|
| 3 |
+
size 634412995
|
pytorch_model-00030-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f46845bd69a7b4e264239329e36730344d98c3f790ab9b0be1390e0fdc4c3a26
|
| 3 |
+
size 634412995
|
pytorch_model-00031-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9dc15d914195e8bc2e6876d6adef4efa480f37c1ff9b66d2f88b678e8e527bf
|
| 3 |
+
size 634412995
|
pytorch_model-00032-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fd0af260490fdd6547db368cf792a4df581ad56603224ef532691be65d5763b
|
| 3 |
+
size 634412995
|
pytorch_model-00033-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17bb7825e4a9c9dbfb0805a55c7407f68376a4ae47f104b57a0d28b53c7264b1
|
| 3 |
+
size 634412995
|
pytorch_model-00034-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a540873386f09c34e931bb01891a161b38a03bd1f4bed0ac30b23eec7380a81
|
| 3 |
+
size 634412995
|
pytorch_model-00035-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e1fd5a9821c0c27eb54b845eeef7473e2e955560d2200e703a9d47f1a2a4372
|
| 3 |
+
size 634412995
|
pytorch_model-00036-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ff3111a5e6d174058a5330602637dbab57b7842a6b262584364c9b245cfe155
|
| 3 |
+
size 634412995
|
pytorch_model-00037-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25f808cff36e50441a370450b64ff229af840845bf45f56f443e32a1af514030
|
| 3 |
+
size 634412995
|
pytorch_model-00038-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71cebc03fa2956b5db45bb81f5a5614757b692043db71e8a7bd721710d9633be
|
| 3 |
+
size 634412995
|
pytorch_model-00039-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5cf85d8e84ab9e4c4566c025e6da2e845ab5f25db2e06482a468943149bca37
|
| 3 |
+
size 634412995
|
pytorch_model-00040-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:465aaa533941f4e48d0173f0767c8d1ad5d9eccea31b658174c476442fe56133
|
| 3 |
+
size 634412995
|
pytorch_model-00041-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09acc284026557d26b70f54e8875b6dbaa81f88027444e886b18a66a6691d4a0
|
| 3 |
+
size 424706495
|
pytorch_model-00042-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d63d92368d2956c58444eeb6e59d6af5cbe74a02fef89531fff1a149380f24cd
|
| 3 |
+
size 327680938
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 26031738880
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00042-of-00042.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00042.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00042.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00042.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00042.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00042.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00042.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00042.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00042.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00042.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00042.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00042.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00042.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00042.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00042.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00042.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00042.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00042.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00042.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00042.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00042.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00042.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00042.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00042.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00042.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00042.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00042.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00042.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00042.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00042.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00042.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00042.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00042.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00042.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00042.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00042.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00042.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00042.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00042.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00042.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00042.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00042.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00042.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00042.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00042.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00042.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00042.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00042.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00042.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00042.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00042.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00042.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00042.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00042.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00042.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00042.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00042.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00042.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00042.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00042.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00042.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00042.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00042.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00042.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00042.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00042.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00042.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00042.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00042.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00042.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00042.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00042.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00042.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00042.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00042.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00042.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00042.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00042.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00042.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00042.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00034-of-00042.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00034-of-00042.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00042.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00035-of-00042.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00035-of-00042.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00042.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00036-of-00042.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00036-of-00042.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00042.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00037-of-00042.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00037-of-00042.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00042.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00038-of-00042.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00038-of-00042.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00037-of-00042.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00039-of-00042.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00039-of-00042.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00042.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00040-of-00042.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00040-of-00042.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00042.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00041-of-00042.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00041-of-00042.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00041-of-00042.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00041-of-00042.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00041-of-00042.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00040-of-00042.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00042.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00042.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00042.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 358 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00042.bin",
|
| 359 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 360 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 361 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 362 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00042.bin",
|
| 363 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 364 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 365 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 366 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00042.bin",
|
| 367 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 368 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00042.bin",
|
| 369 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 370 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 371 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 372 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00042.bin",
|
| 373 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 374 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 375 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 376 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00042.bin",
|
| 377 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 378 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00042.bin",
|
| 379 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 380 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 381 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 382 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00042.bin",
|
| 383 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 384 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 385 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 386 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00042.bin",
|
| 387 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 388 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00042.bin",
|
| 389 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 390 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 391 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 392 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00042.bin",
|
| 393 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 394 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 395 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 396 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00042.bin",
|
| 397 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 398 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00042.bin",
|
| 399 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 400 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 401 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 402 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00042.bin",
|
| 403 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 404 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 405 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 406 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00042.bin",
|
| 407 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 408 |
+
"model.norm.weight": "pytorch_model-00041-of-00042.bin"
|
| 409 |
+
}
|
| 410 |
+
}
|