Upload LlamaForCausalLM
Browse files- config.json +26 -0
- generation_config.json +9 -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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sharpbai/Llama-2-13b-chat-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 13824,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 40,
|
| 15 |
+
"num_hidden_layers": 40,
|
| 16 |
+
"num_key_value_heads": 40,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pretraining_tp": 2,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "float16",
|
| 23 |
+
"transformers_version": "4.31.0",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"temperature": 0.9,
|
| 7 |
+
"top_p": 0.6,
|
| 8 |
+
"transformers_version": "4.31.0"
|
| 9 |
+
}
|
pytorch_model-00001-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:060ad99d5d0a5304e46c58555fe42521816ddb12011bec40d7b1ab93ac352662
|
| 3 |
+
size 537397951
|
pytorch_model-00002-of-00042.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:733ca598a476397f1c7a336741cdb24de4d71c8ee9349ca180e3248e8db92f50
|
| 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:ad22422fd97ceecd3a8ac7784c15d225126f8ad399b667c36cc85e0711dcefca
|
| 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:db0f3649fc4a2431ef4818fe374381bc310eb322b17351b0c93949703cd6e99d
|
| 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:fbb14593fd0aeb157f72a62f9782a9e389d5e4b4e7ea2fb92fb9ebaa472aaafa
|
| 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:b673e6a239befd56abbce8a76a787b97441b40639f3daaf0bfef5f615c529bc2
|
| 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 sha256:908d3aca40396278fbdecc84c7b115ddf178d461abc4393380f57064286ec99d
|
| 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:aa87b07ba74d6df61ec87294efdf51f37c29087d87493378152bcc78f8c892b4
|
| 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:a7da06f3db130861798177e1d2cb52c7468db5f37d5c7fd6e6bddf328a3d7e15
|
| 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 sha256:9ef031e3ceb879774ae6f466180cc0158e673d675f4be4e38d068446d41db252
|
| 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 sha256:84d978aaae0404619da8df5355378f76890355d83e4eae62f73b8cde7a41acc1
|
| 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 sha256:60e02ddbf6054d55cdf2c2346211b8e69967114fdc496d75a184f61274947d68
|
| 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:ca49eab9a4db641f507ae37a5d523b8b2046d749d49226063833735f8186929e
|
| 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:f90a67b9ce41268d467c5e0969cfa9ef96ff2ec39271bf21498008852db3e85d
|
| 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:e34fd0e8b663166e354cdae02ccf7603ffc0091eb962fd97d5bf26bb0035497e
|
| 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 sha256:57882ae98b82064b7133351f00fd9032b8d15b1b23be33381968a5822ef4334b
|
| 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:ff8c43cea95c38f5732bc00481f9c29a85765c4c89e8f329e0a892014d6fcc9c
|
| 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:f1e0e635ca2649f8c26fbd3b1ad55ed50923e611a7be79513c1a675628fabd4b
|
| 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 sha256:3b2f89d34f377466fc32d4cb680a6a1cbcd4f4f4e8d591b877ffe374a1e654da
|
| 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:e387d2a96aa19623efc6f03980f74ad8ab2df675963025b018716388c5be45b0
|
| 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 sha256:3f87959618aa7bfb959440278ea6ca7d912c0e79e52ffead7ef29ce15c957a6b
|
| 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:e1d8e059f428fd39dd908632477bfaede3aaadcb8a7177173dc91b1415624dd1
|
| 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 sha256:2e63c9bd3824835f899e85b6bd449d222ffb0211dfd26ca7f832bce88ff5394e
|
| 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:a5f6252ed3d2960f63629f5b56ef71701ae2f8edc6b8724eafb441042a114dd9
|
| 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:cdd692beb948263a2f3aa734201fa77e6934e0ca8acf8150aba5167eab84222f
|
| 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 sha256:648394c1953b4cb22b5fc9acc9e5d9cae368dbe6e83f2614b563f30e00a61bf1
|
| 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 sha256:0525669cbc7ce74b33e2efe495a78c208c25357dd9f5147536559685a8e24830
|
| 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:fd48113dacb9e74a8eba0cea9c4fbcd98e7cb6cb6675bb4f0fcf7b81ec0631ea
|
| 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 sha256:5903e10c5c9bade225fe2bc52d69f0a429e1be48186454c58d6cfed0f7428a32
|
| 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:ac8312b5a6acd32b3dd22b5549351eeb69c77b0d9894261e6cc2757f5aa72d10
|
| 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 sha256:91cf9ff23214f2001c2305ac49621b3665a71d002798d8fba86ac0d41725884d
|
| 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:f362cb53ad4e5dde2bbb8e81c305deacefa04d754a97cb47281ba4bcec53feea
|
| 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 sha256:9093840ec2ada09c0989f7a83049a52576af2c2128cb109acb7b001b970e005b
|
| 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 sha256:806534f2be975ca8530f59965255aa65cf8a07004e387418e904b218cc7b8414
|
| 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 sha256:25f2b9d54b5f5f9adb5d6e004ff35ea315c7953f043bd9844691bbff598cf90c
|
| 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 sha256:7d9a8a01c1c445f2a1af08a4c843f44cccabf2ac3e6574af365646f5b2d74436
|
| 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:d73811a4c1ed4e30c932fe09bfa7abc9ca3abad49904873a99c66f8427f87b9a
|
| 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 sha256:2b42924681a5243a5f1c7110987a5f12158d0fbbba7aa1024d3b87f68afc23c4
|
| 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 sha256:95eb4e5627ea2eef896fc6e1a92d16c58307255c1f361c707c1de325e8572788
|
| 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 sha256:336b6c3279d324d75f20c992c85436416ac069b0f2dc4996f0139442e724f365
|
| 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:b53ebc54cccec0a9cd96cf2e76a97d12fe6ba8ce8b322e2341bd266fd4a94b97
|
| 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:e9ffe06e5dc8eba175a15777121422bedd838bf4625d1a86fe5bc373808246b7
|
| 3 |
+
size 327680938
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 26031738880
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00042-of-00042.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00042.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00042.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00042.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00042.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00042.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00042.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00042.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00042.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00042.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00042.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00042.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00042.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00042.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00042.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00042.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00042.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00042.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00042.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00042.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00042.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00042.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00042.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00042.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00042.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00042.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00042.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00042.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00042.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00042.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00042.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00042.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00042.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00042.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00042.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00042.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00042.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00042.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00042.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00042.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00042.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00042.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00042.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00042.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00042.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00042.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00042.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00042.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00042.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00042.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00042.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00042.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00042.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00042.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00042.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00042.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00042.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00042.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00042.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00042.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00042.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00042.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00042.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00042.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00042.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00042.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00042.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00042.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00042.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00042.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00042.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00042.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00042.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00042.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00042.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00042.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00042.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00042.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00042.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00042.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00042.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00042.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00042.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00042.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00042.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00042.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00042.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00042.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00042.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00042.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00042.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00042.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00042.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00042.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00042.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00042.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00042.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00042.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00042.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00042.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00042.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00042.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00042.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00042.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00042.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00034-of-00042.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00034-of-00042.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00042.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00033-of-00042.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00035-of-00042.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00035-of-00042.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00042.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00034-of-00042.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00036-of-00042.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00036-of-00042.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00042.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00035-of-00042.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00037-of-00042.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00037-of-00042.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00042.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00036-of-00042.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00038-of-00042.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00038-of-00042.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00037-of-00042.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00037-of-00042.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00039-of-00042.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00039-of-00042.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00042.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00038-of-00042.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00040-of-00042.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00040-of-00042.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00042.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00039-of-00042.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00041-of-00042.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00041-of-00042.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00041-of-00042.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00041-of-00042.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00041-of-00042.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00040-of-00042.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00040-of-00042.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00042.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00042.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00042.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00042.bin",
|
| 358 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00042.bin",
|
| 359 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 360 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 361 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 362 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00042.bin",
|
| 363 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 364 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 365 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 366 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00042.bin",
|
| 367 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00042.bin",
|
| 368 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00042.bin",
|
| 369 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 370 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 371 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 372 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00042.bin",
|
| 373 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 374 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 375 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 376 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00042.bin",
|
| 377 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00042.bin",
|
| 378 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00042.bin",
|
| 379 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 380 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 381 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 382 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00042.bin",
|
| 383 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 384 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 385 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 386 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00042.bin",
|
| 387 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00042.bin",
|
| 388 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00042.bin",
|
| 389 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 390 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 391 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 392 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00042.bin",
|
| 393 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 394 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 395 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 396 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00042.bin",
|
| 397 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00042.bin",
|
| 398 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00042.bin",
|
| 399 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 400 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 401 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00042.bin",
|
| 402 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00042.bin",
|
| 403 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 404 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 405 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 406 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00042.bin",
|
| 407 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00042.bin",
|
| 408 |
+
"model.norm.weight": "pytorch_model-00041-of-00042.bin"
|
| 409 |
+
}
|
| 410 |
+
}
|