commit files to HF hub
Browse files- added_tokens.json +3 -0
- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00034.bin +3 -0
- pytorch_model-00002-of-00034.bin +3 -0
- pytorch_model-00003-of-00034.bin +3 -0
- pytorch_model-00004-of-00034.bin +3 -0
- pytorch_model-00005-of-00034.bin +3 -0
- pytorch_model-00006-of-00034.bin +3 -0
- pytorch_model-00007-of-00034.bin +3 -0
- pytorch_model-00008-of-00034.bin +3 -0
- pytorch_model-00009-of-00034.bin +3 -0
- pytorch_model-00010-of-00034.bin +3 -0
- pytorch_model-00011-of-00034.bin +3 -0
- pytorch_model-00012-of-00034.bin +3 -0
- pytorch_model-00013-of-00034.bin +3 -0
- pytorch_model-00014-of-00034.bin +3 -0
- pytorch_model-00015-of-00034.bin +3 -0
- pytorch_model-00016-of-00034.bin +3 -0
- pytorch_model-00017-of-00034.bin +3 -0
- pytorch_model-00018-of-00034.bin +3 -0
- pytorch_model-00019-of-00034.bin +3 -0
- pytorch_model-00020-of-00034.bin +3 -0
- pytorch_model-00021-of-00034.bin +3 -0
- pytorch_model-00022-of-00034.bin +3 -0
- pytorch_model-00023-of-00034.bin +3 -0
- pytorch_model-00024-of-00034.bin +3 -0
- pytorch_model-00025-of-00034.bin +3 -0
- pytorch_model-00026-of-00034.bin +3 -0
- pytorch_model-00027-of-00034.bin +3 -0
- pytorch_model-00028-of-00034.bin +3 -0
- pytorch_model-00029-of-00034.bin +3 -0
- pytorch_model-00030-of-00034.bin +3 -0
- pytorch_model-00031-of-00034.bin +3 -0
- pytorch_model-00032-of-00034.bin +3 -0
- pytorch_model-00033-of-00034.bin +3 -0
- pytorch_model-00034-of-00034.bin +3 -0
- pytorch_model.bin.index.json +330 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "alpaca-7b-merged",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"torch_dtype": "float16",
|
| 20 |
+
"transformers_version": "4.30.1",
|
| 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": "4.30.1"
|
| 7 |
+
}
|
pytorch_model-00001-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aec1f7428942a83387eb237683094a23d23689aadef6fc2dbb1d93d5dfacb3b
|
| 3 |
+
size 396372671
|
pytorch_model-00002-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:782c6cfe6773b8e0a299faeb6cb80bf037bab2a6d5bfa1219b5bad7f7f0dddf8
|
| 3 |
+
size 404770755
|
pytorch_model-00003-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cec4a07916da78a26890de181c2caa64acba120c159a60f032dde97c4a8c2103
|
| 3 |
+
size 404770755
|
pytorch_model-00004-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0fc49849624a1d09f1a53571c572b6fba1fc7f579c98081ca95f3568f7938e9
|
| 3 |
+
size 404770755
|
pytorch_model-00005-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c9cecb98223b8463663fae243df1326d4a39001a0c671683a419ff06b6b1afa
|
| 3 |
+
size 404770755
|
pytorch_model-00006-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08aece55bb12927709f91c2ed9d7e308a02190332d2aa9df0e73925adac32aa0
|
| 3 |
+
size 404770755
|
pytorch_model-00007-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46b59933c2dadaeba9055320217f4fbba63f235c7eeec33aa9ed14e92df26c99
|
| 3 |
+
size 404770755
|
pytorch_model-00008-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4999d51e214b3794bca9fce578d50babececa4f6aa874bd506d904122587f254
|
| 3 |
+
size 404770755
|
pytorch_model-00009-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:157538e3f8d6f09e105c8bcc39a02c74be491d74856a798225670172dfd6671c
|
| 3 |
+
size 404770755
|
pytorch_model-00010-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2f1b8e5f5d05f82572fd73c355bf05570b2656a3d3407bb154e58fb46050ec5
|
| 3 |
+
size 404770755
|
pytorch_model-00011-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:815e80f3e07fb51896150954615110de2dda32882b7464f5a3161153f9700e6e
|
| 3 |
+
size 404770755
|
pytorch_model-00012-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c718c9f4e0fd09f0d7746d0db5a191cb0c7aa0050e5656acc9101f46c2f24e3
|
| 3 |
+
size 404770755
|
pytorch_model-00013-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df16e77c3cbbefef908354b6aedad2de18c332cce496d54f2ff55ff3cbd61163
|
| 3 |
+
size 404770755
|
pytorch_model-00014-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8143cc997e100ae4aa828774738b97399e00ffe25cb1d793e7e4e59ae08a1648
|
| 3 |
+
size 404770755
|
pytorch_model-00015-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:272f4d56ddb47e9dab47357e9148f10175ee65b977135606d2b54a8d869a5c3c
|
| 3 |
+
size 404770755
|
pytorch_model-00016-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4baff3985ab6c9c89e5ee4455d25ea54280eb566baca8f93e2400bed865a95bc
|
| 3 |
+
size 404770755
|
pytorch_model-00017-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3a2320e956ce306cee05ee8ddf08733c964ad8f7bcdd451c6bf7c5796984479
|
| 3 |
+
size 404770755
|
pytorch_model-00018-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fd32f63ced8241184840b7047f2287c9cbbd193e0769320fc4d2660fadc347b
|
| 3 |
+
size 404770755
|
pytorch_model-00019-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:947204eb23ecb8e585efa29491b7cb49ee3f07b69efd1b09b51751f9746bf439
|
| 3 |
+
size 404770755
|
pytorch_model-00020-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf6251414ac0723b1d4c82cdabe230e6478d61df39ff8a75f5af487f56116f6c
|
| 3 |
+
size 404770755
|
pytorch_model-00021-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec04c0ea3a22035c3642d35cfd585e861d1358950849dc3f6b5da4e15f0a8620
|
| 3 |
+
size 404770755
|
pytorch_model-00022-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfcab1200d267d1db59419cfc5cb93503ba43f3581d47a9f7a9602e4f0e69f34
|
| 3 |
+
size 404770755
|
pytorch_model-00023-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a667f05630e2488201f585d589f0a889dec1b010b7449a6a71767297b7cdf89
|
| 3 |
+
size 404770755
|
pytorch_model-00024-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5243eb2f34bdd59202e4ce72fb8f83974a8fc57213ada4936b036e2a62175fae
|
| 3 |
+
size 404770755
|
pytorch_model-00025-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b624aff546288582a0c9dd2fabd7305e058b5688b57f04f144d7e71d38c6031
|
| 3 |
+
size 404770755
|
pytorch_model-00026-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f48b3e1ed617e6b88ed2bb2610c7999d0c7ebc50d9b7c134eb4ae43bee129e78
|
| 3 |
+
size 404770755
|
pytorch_model-00027-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bd72bc047e91da4f1c6c4ec901b2d7bb9329d0b3a21965fcf5ca304a69806d9
|
| 3 |
+
size 404770755
|
pytorch_model-00028-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bd6fe47c611f069c14aa9977e4e0bc26406b543e0dad3f21454cf1413c0a869
|
| 3 |
+
size 404770755
|
pytorch_model-00029-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:040e4181522a1f057b261d673ec1685bf6008031ed852bb931213ba5bdc25917
|
| 3 |
+
size 404770755
|
pytorch_model-00030-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a76c74ec9f91982ec5c8301798ca76bfc5c08ad8988195361b93e756088f3ce
|
| 3 |
+
size 404770755
|
pytorch_model-00031-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dad9b3106ef098686534a58b6bb280dad0d4639e934a58e133baecbc8a359761
|
| 3 |
+
size 404770755
|
pytorch_model-00032-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64662501649154dc846910ebd82206d4c025932c5715c9c296a7fc47f0bf8801
|
| 3 |
+
size 404770755
|
pytorch_model-00033-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:805c3dc9879f7185e6b068a4214be634a68b4858525dcf7bddd0094d215ef558
|
| 3 |
+
size 270559679
|
pytorch_model-00034-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb6d8ac32c0fef962918da1ef9b3a29cf013040f0a183ad8135e6c70d21d31ba
|
| 3 |
+
size 262153130
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476855808
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00034-of-00034.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00034.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00034.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00034.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00034.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00034.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00034.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00034.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00034.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00034.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00034.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00034.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00034.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00034.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00034.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00034.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00034.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00034.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00034.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00034.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00034.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00034.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00034.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00034.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00034.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00034.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00034.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00034.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00034.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00034.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00034.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00034.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00034.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00034.bin",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00034.bin",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00034.bin",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00034.bin",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00034.bin",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00034.bin",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00034.bin",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 328 |
+
"model.norm.weight": "pytorch_model-00033-of-00034.bin"
|
| 329 |
+
}
|
| 330 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "[PAD]",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"model_max_length": 512,
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"padding_side": "right",
|
| 24 |
+
"sp_model_kwargs": {},
|
| 25 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|