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/openchat_8192",
|
| 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": 8192,
|
| 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": 32001
|
| 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 sha256:76001b97ec3b57f526a2f2d9be37f0cbaefbd367b796672bc165893a95fb5cff
|
| 3 |
+
size 537408191
|
pytorch_model-00002-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30cecdc66370bae5b7951c4b22eeae8d4516d13514bffb4c2313a68716c3cb1c
|
| 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 sha256:21b1cb6cb165da92282b5a57e22b4c091bfecd277d75c441b6f7554069734885
|
| 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:f45bceba39bf9d1dff79ec957bdb1fac3e64ef8aac645a12f4da9de850d863ff
|
| 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 sha256:920116afaefb58a68247ea0db50c196e1fe494d1bc373cf6101441fd0a7a3737
|
| 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 sha256:962556640fe5fe408a8c569b7ebc9ba021660bc340d48b6bc13d27fbfd21f384
|
| 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 sha256:1a05deab93e54f346612b3f35513d691531ca184c06d70916a2d926d3f29b91f
|
| 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 sha256:62c792cef1f6dd0d1d653835586a99ec5eb697efee370fc7841c13a24450fb60
|
| 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:f6d8800c9883cff803c1a074db9608c366da40864e7f6aed38241a8230ae6825
|
| 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 sha256:0dd171b1f8c0f9d8c7009d34841ddf5cdec98c0bd83c30cb3ab534addfb879e9
|
| 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:f02fe1cd1f09067cf7b36790055d9c756e0ad5c5f61314fd8ee86b194f655597
|
| 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 sha256:21046c1bac24db42236a8ed490ee2ad90bacaef41156795cf9f9e9e7b24eae52
|
| 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 sha256:7c957f29ca1bb447587cb26c67aec90d8255bf00623965ae4dd9273e0da4016d
|
| 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 sha256:413c8bbea89d843c5cc8df5d72686145ea0e826a25f53226c29c8c5464adf3b7
|
| 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 sha256:6fe597076a366abae9230153d5d4f35e2428da3be1affcb38fd6d5ef89ca0b0d
|
| 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 sha256:3e6a1dc623cdcc98e9f70a21d258f83ab2cd9d28fa591d46d043f3b8b65dc59c
|
| 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 sha256:2c1c7dbc3ac35201150d57a4175d8e30ce9f6bcb9b5e7c4053f600f354f36ad0
|
| 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 sha256:3404788d8f4b63f49ea11ecca793acdf3d933a4cde8b012d99999dae5dc49798
|
| 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 sha256:015ea82fadd2689c412864f9b5a1d31bbb1d020a112173d9d4195ead82052a64
|
| 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:ad349a558b1b028a8879040b2c607b80e5e40f01f49a4af847c07d52dc1335d3
|
| 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 sha256:8a3f66fcc21905322343d508cc11c739f97cac5bc68f56c57d915b3613f1d779
|
| 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:adf93067e62b029c7d7ade0b1c594be62186ee63cd1f932a4fb8ca68ec26b144
|
| 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:eea660bcbd85a0e980b70d15ffc92747fbb802ea8cde92ca8ce28921b7b5168c
|
| 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:c69139b05dfc931145465dc780b80f1280984b662ecec8853eee7e421eb4f364
|
| 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:e8f80f37b8f79f288b7e62ac4d8d0ebb95617fcee21d145e24b4e164b55709f2
|
| 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:ad27f0b80ddf75e2b94c6ef26ea72bfc43e14093257f39ce710e08cdd22d629e
|
| 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 sha256:6c42c44050c4f5e03c292c8bd5fc91a30027742be25e3d769f2536b8593f3165
|
| 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 sha256:09bd3f716de05712fd0f48bd662d79b1f07d296c9cf7252ddc3c220a4e3e936b
|
| 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:e80127c44d9ad10523faea12faeda172c2c9a67a8040c7f7744389c14a728f72
|
| 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:b30cd244e0172bfbe7a1e38b05a11fdadc4c9da6b385425dd5d029bd3be508be
|
| 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 sha256:6f763f1ae731d44e8fffd5807b8657fcec7f3c6353d5ed6e89250b589ee4d4d6
|
| 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:f3c0e9417906d02715b053be5e772a3679f48d8eb4f6108c751f61c5a53b1318
|
| 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 sha256:5c6b0498a6849cabb1ea31a892377eaae183403b0d843ee5c216f32154a485af
|
| 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 sha256:2922e0a4dae50e7c928a9d965edc6f7992389ca17267a907d4e4cffa10325e4f
|
| 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 sha256:53cb587ce84a666df1b52807c23d60fcdbdb81083b51e273054468cb2c5659f3
|
| 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:ed5f4ce2aeb098ab18c1e4ea370742f06a7ede49b46e8787d805b34cd3b0bcb4
|
| 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 sha256:1d6ba7b32d74b1c1172df00c718a1e50cdcd088245c08a9bd5d732f9e4383772
|
| 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:b30621f3890bdbd17826d46e49558911bbb6cdd803849d0b0171fb6d2809173c
|
| 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 sha256:2331579abdf3904076feadbb9c85694d675f7195264b0483b803d1a29dc4f2f1
|
| 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:d3ff628d927126d9e830125977e5e7c10430e042a7f713868adb6cf7bbd4ddfe
|
| 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 sha256:0d21a84a1a09045381677793e709d6a853ba54e9cb67a862e5b6964cc3b71eb1
|
| 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 sha256:004f6f465a003c6438cbcc185fbf63448c48df68e0a23a010b1ca6124f9ea4e0
|
| 3 |
+
size 327691178
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 26031759360
|
| 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 |
+
}
|