Upload BaichuanForCausalLM
Browse files- config.json +30 -0
- generation_config.json +14 -0
- pytorch_model-00001-of-00029.bin +3 -0
- pytorch_model-00002-of-00029.bin +3 -0
- pytorch_model-00003-of-00029.bin +3 -0
- pytorch_model-00004-of-00029.bin +3 -0
- pytorch_model-00005-of-00029.bin +3 -0
- pytorch_model-00006-of-00029.bin +3 -0
- pytorch_model-00007-of-00029.bin +3 -0
- pytorch_model-00008-of-00029.bin +3 -0
- pytorch_model-00009-of-00029.bin +3 -0
- pytorch_model-00010-of-00029.bin +3 -0
- pytorch_model-00011-of-00029.bin +3 -0
- pytorch_model-00012-of-00029.bin +3 -0
- pytorch_model-00013-of-00029.bin +3 -0
- pytorch_model-00014-of-00029.bin +3 -0
- pytorch_model-00015-of-00029.bin +3 -0
- pytorch_model-00016-of-00029.bin +3 -0
- pytorch_model-00017-of-00029.bin +3 -0
- pytorch_model-00018-of-00029.bin +3 -0
- pytorch_model-00019-of-00029.bin +3 -0
- pytorch_model-00020-of-00029.bin +3 -0
- pytorch_model-00021-of-00029.bin +3 -0
- pytorch_model-00022-of-00029.bin +3 -0
- pytorch_model-00023-of-00029.bin +3 -0
- pytorch_model-00024-of-00029.bin +3 -0
- pytorch_model-00025-of-00029.bin +3 -0
- pytorch_model-00026-of-00029.bin +3 -0
- pytorch_model-00027-of-00029.bin +3 -0
- pytorch_model-00028-of-00029.bin +3 -0
- pytorch_model-00029-of-00029.bin +3 -0
- pytorch_model.bin.index.json +290 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"_name_or_path": "baichuan-inc/Baichuan2-13B-Chat",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BaichuanForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "baichuan-inc/Baichuan2-13B-Chat--configuration_baichuan.BaichuanConfig",
|
| 9 |
+
"AutoModelForCausalLM": "baichuan-inc/Baichuan2-13B-Chat--modeling_baichuan.BaichuanForCausalLM"
|
| 10 |
+
},
|
| 11 |
+
"bos_token_id": 1,
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 5120,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 13696,
|
| 17 |
+
"model_max_length": 4096,
|
| 18 |
+
"model_type": "baichuan",
|
| 19 |
+
"num_attention_heads": 40,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"tokenizer_class": "BaichuanTokenizer",
|
| 25 |
+
"torch_dtype": "float16",
|
| 26 |
+
"transformers_version": "4.33.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 125696,
|
| 29 |
+
"z_loss_weight": 0
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"assistant_token_id": 196,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"max_new_tokens": 2048,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 0.3,
|
| 10 |
+
"top_k": 5,
|
| 11 |
+
"top_p": 0.85,
|
| 12 |
+
"transformers_version": "4.33.1",
|
| 13 |
+
"user_token_id": 195
|
| 14 |
+
}
|
pytorch_model-00001-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7e711acc4d8d8ae0f56775b609b31b077a1dc600650a4698e1e2201a843486f
|
| 3 |
+
size 1287127978
|
pytorch_model-00002-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75f13ba159765fdaf4302bcdd97356f26bf3e1549d3c670c7175486b7922e859
|
| 3 |
+
size 980442755
|
pytorch_model-00003-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0358fca96a8431ca5022fdc31e18bbffd80247020025d9ef5e4f20c70edc7166
|
| 3 |
+
size 910995413
|
pytorch_model-00004-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa55810783ce4d3a793de63802beb7ec69c530295533393e19e97054a38908eb
|
| 3 |
+
size 980442755
|
pytorch_model-00005-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a33b729f490bb27b4cef7d3e427a73d8c00b3e02ebd942511b183da524b78aaa
|
| 3 |
+
size 910995413
|
pytorch_model-00006-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1621945875f1ca9e6d15ab84346a90a56aa5c777fd25bdf6cd9ae6f948c1a80
|
| 3 |
+
size 980442755
|
pytorch_model-00007-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:709e4cdb76355ad2bba0650b1b7bcce2c89f5c271eeb305dcc45249bced914ee
|
| 3 |
+
size 910995413
|
pytorch_model-00008-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c349a7f9d83a91c8a64f9acbbf1745d19e358a300c2a849dab3cb97e87fade90
|
| 3 |
+
size 980442755
|
pytorch_model-00009-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9da59abf15a6fda20e77cb93f2a7dd6e2a16f91fb062074b7046f11027ce4cbf
|
| 3 |
+
size 910995413
|
pytorch_model-00010-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a8e457fb4b2e044d32b13959ebefc1bb2109096305c8b11e49ece3f0a0e173d
|
| 3 |
+
size 980442819
|
pytorch_model-00011-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddd4305864def7706557d4906b335259f61791bff71774642e36bab4684a27fc
|
| 3 |
+
size 910995413
|
pytorch_model-00012-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a6174428422a2e96cc9981ca54d56e67da6cb89f03e0f62bd8ca2a3de15a393
|
| 3 |
+
size 980442819
|
pytorch_model-00013-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:102d7aa8699f53aeb72b323e05887d1168a83c5093ce97d160f6719b1f6f109d
|
| 3 |
+
size 910995413
|
pytorch_model-00014-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5fe326c98cdee36d3b759c6f656a7d6ed2fee7f361f71ddff00832a3117589
|
| 3 |
+
size 980442819
|
pytorch_model-00015-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18d908f8971ec4ba9e85af17d56ee33686f001197325597a1afd7e51a65c946b
|
| 3 |
+
size 910995413
|
pytorch_model-00016-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25708faf6d86cef3538a2274f51676efd459c47ea583d1384e2c17f4854160aa
|
| 3 |
+
size 980442819
|
pytorch_model-00017-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e954349e1de7285295c12df5391e3560d0eef2a555ee4c4a3759a020e21629
|
| 3 |
+
size 910995413
|
pytorch_model-00018-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70fc1f4367d655cd909fd69f4e484d343224899c137618b382f69dd993eb4abd
|
| 3 |
+
size 980442819
|
pytorch_model-00019-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aa6602c47789b6a7445c2046d5beacce0ec2ecd4af7ca30a88edb42026c2c03
|
| 3 |
+
size 910995413
|
pytorch_model-00020-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:019c4a42a783eb010ae6773313d5d57eb6a237acfadb7da46743186e8efe917d
|
| 3 |
+
size 980442819
|
pytorch_model-00021-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40e28a7997e248266a6954fcc4c7cf587c64e7a99d926abd387eedd9b2c705bf
|
| 3 |
+
size 910995413
|
pytorch_model-00022-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a34cd43008264682bb0544aed64fd580c4ae3ca35298af37e94fbeeb13299717
|
| 3 |
+
size 980442819
|
pytorch_model-00023-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9137f0126f03768317a8963f34cd88f5c10fe454e99e7c0e5aee21769a6841ea
|
| 3 |
+
size 910995413
|
pytorch_model-00024-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57a4054db785975e9ccc05590469e2063eb9aaeef81b8c56a8bf8a880f4138c4
|
| 3 |
+
size 980442819
|
pytorch_model-00025-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6a626ed0bfc3c16f80bfaff7310af491f8d1507a02ba98d3352707457646901
|
| 3 |
+
size 910995413
|
pytorch_model-00026-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6df46ffe0186c133db3d7861f076513e55917492316e5a36d257628b726a68c
|
| 3 |
+
size 980442819
|
pytorch_model-00027-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e41dede436a2aff974787ff8fb047e4e908eaee350ef84dbc07284f32a338cec
|
| 3 |
+
size 910995413
|
pytorch_model-00028-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b3d019253023247cf9bf0ac67c55cb64e9a6a9bb2e9ffa586950fc2ad0f8a8c
|
| 3 |
+
size 630490145
|
pytorch_model-00029-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8df5bf762b0dc5b272be0237ca0ffe3f441deeac68f07145bf76f27463590c4
|
| 3 |
+
size 1287127978
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,290 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 27793336320
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00029-of-00029.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00029.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 13 |
+
"model.layers.0.self_attn.W_pack.weight": "pytorch_model-00002-of-00029.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 15 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 16 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 17 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 18 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 19 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 20 |
+
"model.layers.1.self_attn.W_pack.weight": "pytorch_model-00002-of-00029.bin",
|
| 21 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 22 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 23 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 24 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 25 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 26 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 27 |
+
"model.layers.10.self_attn.W_pack.weight": "pytorch_model-00008-of-00029.bin",
|
| 28 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 29 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 30 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 31 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 32 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 33 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 34 |
+
"model.layers.11.self_attn.W_pack.weight": "pytorch_model-00009-of-00029.bin",
|
| 35 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 36 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
| 37 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 38 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 39 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 40 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
| 41 |
+
"model.layers.12.self_attn.W_pack.weight": "pytorch_model-00010-of-00029.bin",
|
| 42 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 43 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 44 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 45 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 46 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 47 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 48 |
+
"model.layers.13.self_attn.W_pack.weight": "pytorch_model-00010-of-00029.bin",
|
| 49 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 50 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 51 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 52 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 53 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 54 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 55 |
+
"model.layers.14.self_attn.W_pack.weight": "pytorch_model-00011-of-00029.bin",
|
| 56 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 57 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 58 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 59 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 60 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 61 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 62 |
+
"model.layers.15.self_attn.W_pack.weight": "pytorch_model-00012-of-00029.bin",
|
| 63 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 64 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 65 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 66 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 67 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 68 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 69 |
+
"model.layers.16.self_attn.W_pack.weight": "pytorch_model-00012-of-00029.bin",
|
| 70 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 71 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 72 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 73 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 74 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 75 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 76 |
+
"model.layers.17.self_attn.W_pack.weight": "pytorch_model-00013-of-00029.bin",
|
| 77 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 78 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 79 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 80 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 81 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 82 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 83 |
+
"model.layers.18.self_attn.W_pack.weight": "pytorch_model-00014-of-00029.bin",
|
| 84 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 85 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 86 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 87 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 88 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 89 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 90 |
+
"model.layers.19.self_attn.W_pack.weight": "pytorch_model-00014-of-00029.bin",
|
| 91 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 92 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 93 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 94 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 95 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 96 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 97 |
+
"model.layers.2.self_attn.W_pack.weight": "pytorch_model-00003-of-00029.bin",
|
| 98 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 99 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 100 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 101 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 102 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 103 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 104 |
+
"model.layers.20.self_attn.W_pack.weight": "pytorch_model-00015-of-00029.bin",
|
| 105 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 106 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 107 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 108 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 109 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 110 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 111 |
+
"model.layers.21.self_attn.W_pack.weight": "pytorch_model-00016-of-00029.bin",
|
| 112 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 113 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 114 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 115 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 116 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 117 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 118 |
+
"model.layers.22.self_attn.W_pack.weight": "pytorch_model-00016-of-00029.bin",
|
| 119 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 120 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 121 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 122 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 123 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 124 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 125 |
+
"model.layers.23.self_attn.W_pack.weight": "pytorch_model-00017-of-00029.bin",
|
| 126 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 127 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 128 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 129 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 130 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 131 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 132 |
+
"model.layers.24.self_attn.W_pack.weight": "pytorch_model-00018-of-00029.bin",
|
| 133 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 134 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 135 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 136 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 137 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 138 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 139 |
+
"model.layers.25.self_attn.W_pack.weight": "pytorch_model-00018-of-00029.bin",
|
| 140 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 141 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 142 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 143 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 144 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 145 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 146 |
+
"model.layers.26.self_attn.W_pack.weight": "pytorch_model-00019-of-00029.bin",
|
| 147 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 148 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
| 149 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 150 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 151 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 152 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
| 153 |
+
"model.layers.27.self_attn.W_pack.weight": "pytorch_model-00020-of-00029.bin",
|
| 154 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 155 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 156 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 157 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 158 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 159 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 160 |
+
"model.layers.28.self_attn.W_pack.weight": "pytorch_model-00020-of-00029.bin",
|
| 161 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 162 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 163 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 164 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 165 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 166 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 167 |
+
"model.layers.29.self_attn.W_pack.weight": "pytorch_model-00021-of-00029.bin",
|
| 168 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 169 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 170 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 171 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 172 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 173 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 174 |
+
"model.layers.3.self_attn.W_pack.weight": "pytorch_model-00004-of-00029.bin",
|
| 175 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 176 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 177 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 178 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 179 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 180 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 181 |
+
"model.layers.30.self_attn.W_pack.weight": "pytorch_model-00022-of-00029.bin",
|
| 182 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 183 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 184 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 185 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 186 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 187 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 188 |
+
"model.layers.31.self_attn.W_pack.weight": "pytorch_model-00022-of-00029.bin",
|
| 189 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 190 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 191 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 192 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 193 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 194 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 195 |
+
"model.layers.32.self_attn.W_pack.weight": "pytorch_model-00023-of-00029.bin",
|
| 196 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 197 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 198 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 199 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 200 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 201 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 202 |
+
"model.layers.33.self_attn.W_pack.weight": "pytorch_model-00024-of-00029.bin",
|
| 203 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 204 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 205 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 206 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 207 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 208 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 209 |
+
"model.layers.34.self_attn.W_pack.weight": "pytorch_model-00024-of-00029.bin",
|
| 210 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 211 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 212 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 213 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 214 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 215 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 216 |
+
"model.layers.35.self_attn.W_pack.weight": "pytorch_model-00025-of-00029.bin",
|
| 217 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 218 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 219 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 220 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 221 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 222 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 223 |
+
"model.layers.36.self_attn.W_pack.weight": "pytorch_model-00026-of-00029.bin",
|
| 224 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 225 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 226 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 227 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 228 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 229 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 230 |
+
"model.layers.37.self_attn.W_pack.weight": "pytorch_model-00026-of-00029.bin",
|
| 231 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 232 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 233 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 234 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 235 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 236 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 237 |
+
"model.layers.38.self_attn.W_pack.weight": "pytorch_model-00027-of-00029.bin",
|
| 238 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 239 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 240 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 241 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 242 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 243 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 244 |
+
"model.layers.39.self_attn.W_pack.weight": "pytorch_model-00028-of-00029.bin",
|
| 245 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 246 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 247 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 248 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 249 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 250 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 251 |
+
"model.layers.4.self_attn.W_pack.weight": "pytorch_model-00004-of-00029.bin",
|
| 252 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 253 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 254 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 255 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 256 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 257 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 258 |
+
"model.layers.5.self_attn.W_pack.weight": "pytorch_model-00005-of-00029.bin",
|
| 259 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 265 |
+
"model.layers.6.self_attn.W_pack.weight": "pytorch_model-00006-of-00029.bin",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 267 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 268 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 269 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 270 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 271 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 272 |
+
"model.layers.7.self_attn.W_pack.weight": "pytorch_model-00006-of-00029.bin",
|
| 273 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 274 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 275 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 276 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 277 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 278 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 279 |
+
"model.layers.8.self_attn.W_pack.weight": "pytorch_model-00007-of-00029.bin",
|
| 280 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 281 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 282 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 283 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 284 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 285 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 286 |
+
"model.layers.9.self_attn.W_pack.weight": "pytorch_model-00008-of-00029.bin",
|
| 287 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 288 |
+
"model.norm.weight": "pytorch_model-00028-of-00029.bin"
|
| 289 |
+
}
|
| 290 |
+
}
|