Upload LlamaForCausalLM
Browse files- config.json +24 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00035.bin +3 -0
- pytorch_model-00002-of-00035.bin +3 -0
- pytorch_model-00003-of-00035.bin +3 -0
- pytorch_model-00004-of-00035.bin +3 -0
- pytorch_model-00005-of-00035.bin +3 -0
- pytorch_model-00006-of-00035.bin +3 -0
- pytorch_model-00007-of-00035.bin +3 -0
- pytorch_model-00008-of-00035.bin +3 -0
- pytorch_model-00009-of-00035.bin +3 -0
- pytorch_model-00010-of-00035.bin +3 -0
- pytorch_model-00011-of-00035.bin +3 -0
- pytorch_model-00012-of-00035.bin +3 -0
- pytorch_model-00013-of-00035.bin +3 -0
- pytorch_model-00014-of-00035.bin +3 -0
- pytorch_model-00015-of-00035.bin +3 -0
- pytorch_model-00016-of-00035.bin +3 -0
- pytorch_model-00017-of-00035.bin +3 -0
- pytorch_model-00018-of-00035.bin +3 -0
- pytorch_model-00019-of-00035.bin +3 -0
- pytorch_model-00020-of-00035.bin +3 -0
- pytorch_model-00021-of-00035.bin +3 -0
- pytorch_model-00022-of-00035.bin +3 -0
- pytorch_model-00023-of-00035.bin +3 -0
- pytorch_model-00024-of-00035.bin +3 -0
- pytorch_model-00025-of-00035.bin +3 -0
- pytorch_model-00026-of-00035.bin +3 -0
- pytorch_model-00027-of-00035.bin +3 -0
- pytorch_model-00028-of-00035.bin +3 -0
- pytorch_model-00029-of-00035.bin +3 -0
- pytorch_model-00030-of-00035.bin +3 -0
- pytorch_model-00031-of-00035.bin +3 -0
- pytorch_model-00032-of-00035.bin +3 -0
- pytorch_model-00033-of-00035.bin +3 -0
- pytorch_model-00034-of-00035.bin +3 -0
- pytorch_model-00035-of-00035.bin +3 -0
- pytorch_model.bin.index.json +330 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sharpbai/baichuan-llama-7b",
|
| 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 |
+
"max_sequence_length": 2048,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float16",
|
| 21 |
+
"transformers_version": "4.30.1",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 64000
|
| 24 |
+
}
|
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-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf02c4d7b83fa495ef73f290168a195ea899d0744f0fe32194046846bd87efe0
|
| 3 |
+
size 537
|
pytorch_model-00002-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aff8e9aa72626b49788fd10b0190a35779e5443c7571355b81f937320c06b10
|
| 3 |
+
size 524288938
|
pytorch_model-00003-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a58d201beddcbe8d61fd7858d68a307680487c63e6727fd722a0ccce3ef5e8aa
|
| 3 |
+
size 404770755
|
pytorch_model-00004-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b47f37dc39b3d09b5e79979c403457593c1f3f8f543592228e35d1da2edf14c
|
| 3 |
+
size 404770755
|
pytorch_model-00005-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cc37f8625686306be81615323b4a7a1eff3b10fc7fd663346f09b2628d42f5f
|
| 3 |
+
size 404770755
|
pytorch_model-00006-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ef06986f4799654f8a5d08eb2bac6b258f7593652ff88843cc6e84018d3dde6
|
| 3 |
+
size 404770755
|
pytorch_model-00007-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53c4305c4cabff12f764cf62ff9ce30ba8ceb9071b55a666f86bdb66c339cd89
|
| 3 |
+
size 404770755
|
pytorch_model-00008-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b38e58cd44fd0b148df8123853a99f35046946bd5684543102f3aed14bbda57
|
| 3 |
+
size 404770755
|
pytorch_model-00009-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6a89d66fc6e86a3199a37d05e788d6382df06e6a570c8f494952ebe4ec58c7c
|
| 3 |
+
size 404770755
|
pytorch_model-00010-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11f7ebd06da95518e32a5bfc34fb8331ce7d77180b180757b7b7783018482884
|
| 3 |
+
size 404770755
|
pytorch_model-00011-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0bc25da1357b6f54465e2adea4fd56ad2157b49b19e2ae887bf4a99974f10d6
|
| 3 |
+
size 404770755
|
pytorch_model-00012-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1fefc4110cc974d07cc24d4d25fd12373c3349763811406da85dca0b80032e3
|
| 3 |
+
size 404770755
|
pytorch_model-00013-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c68e6d45e3c0d3e671241fef5a54410e73cafbed6d34af2e88419b7bbd5cc58
|
| 3 |
+
size 404770755
|
pytorch_model-00014-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dc9ce39feebb8ead8f62b63787a6636036d1a66032ca3f4ba61f25e2a0e3158
|
| 3 |
+
size 404770755
|
pytorch_model-00015-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:282a868bf58f06bb794e50ffe1adf619bb9c7423d6f561c0c55135ef81016c2c
|
| 3 |
+
size 404770755
|
pytorch_model-00016-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73140e7cf36ff63140fa5c69a35a05488cdfe6ecaca824c7b1fc1c6b2840f6ac
|
| 3 |
+
size 404770755
|
pytorch_model-00017-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:334e7362db376ef72404f47956da7409b46210da522f0455e0acfaf3bd61253a
|
| 3 |
+
size 404770755
|
pytorch_model-00018-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d6004fd580726de970aaf022ca7c31ef2392d2546abc372a19e05f7d13df088
|
| 3 |
+
size 404770755
|
pytorch_model-00019-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fea28e83b599a90c7788cc490bc3eab2d2bb0a55f9ae0c5b1bc4033df6ff13b
|
| 3 |
+
size 404770755
|
pytorch_model-00020-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02cd1f688d898c0ec520525090c57fe1079aa0de348d0d98120e366027cc325e
|
| 3 |
+
size 404770755
|
pytorch_model-00021-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf8debd7f2de6e9711c9cbb962e14841be75da19c70c64d5e674bf04c975c2b5
|
| 3 |
+
size 404770755
|
pytorch_model-00022-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b539648f5373ef85802da2c4fa5b55a598d522a9990d49b3ba4b7b985bc1a31
|
| 3 |
+
size 404770755
|
pytorch_model-00023-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89a8f5d9347edd7f6948ddea298f311a8214dcac042e6d349f16280669d8bc01
|
| 3 |
+
size 404770755
|
pytorch_model-00024-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e4e5b2aadad168f0e2973571d68347997d991e4a508ed486399b977e5da3a20
|
| 3 |
+
size 404770755
|
pytorch_model-00025-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78293fb0872c6a4505328b198955059cb737bfaf63d546e5d9df09282b2ebfb3
|
| 3 |
+
size 404770755
|
pytorch_model-00026-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:214012761aec3ec0fa1b0dd8da4c6137728cfe5cddc22309741dd5daa726b71f
|
| 3 |
+
size 404770755
|
pytorch_model-00027-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9565cfcc5a662465bb63a71caa734dcde97754b56f44ff89001cf0ebf24b4c3
|
| 3 |
+
size 404770755
|
pytorch_model-00028-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf68aee690459fca7fe0769aa608bd693be4503961810b67de82bceaba0b3293
|
| 3 |
+
size 404770755
|
pytorch_model-00029-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f4e6e28186d2215f98870be39910f14d4ab9339d6d90ee2b584745f3da8592a
|
| 3 |
+
size 404770755
|
pytorch_model-00030-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7c82734b75dec2155ab846e3022eec47244c15feec01a102d82645061b0bb7c
|
| 3 |
+
size 404770755
|
pytorch_model-00031-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23d3dbe0fd607d266b25ef4533210c2a592b456cd6aa568f869ab357f21a558e
|
| 3 |
+
size 404770755
|
pytorch_model-00032-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40aacdbac2649cbaa276ff4427eadea794a0fda378275a01a0265ff256e7c6bc
|
| 3 |
+
size 404770755
|
pytorch_model-00033-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae4ce25b4d49d14771e7a69df3fce2ae8a9e6084cd9e2b1bd90a818c9a8aff03
|
| 3 |
+
size 404770755
|
pytorch_model-00034-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad1871fdb204b4c9a6b83c030520d695da13a986f011a93b035090c841f7db4
|
| 3 |
+
size 404779221
|
pytorch_model-00035-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587eaed49ee9e8ca1e5dac03ee8621ddfc3d3a7d1eae18e895d5134fedb079ca
|
| 3 |
+
size 524288938
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14001127424
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00035-of-00035.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00002-of-00035.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00035.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00035.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00035.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00035.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00035.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00035.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00013-of-00035.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00013-of-00035.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00035.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00014-of-00035.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00014-of-00035.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00035.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00015-of-00035.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00015-of-00035.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00035.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00016-of-00035.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00016-of-00035.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00035.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00017-of-00035.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00017-of-00035.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00035.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00018-of-00035.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00018-of-00035.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00035.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00019-of-00035.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00019-of-00035.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00035.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00020-of-00035.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00020-of-00035.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00035.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00021-of-00035.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00021-of-00035.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00035.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00022-of-00035.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00022-of-00035.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00035.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00035.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00035.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00035.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00023-of-00035.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00023-of-00035.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00035.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00024-of-00035.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00024-of-00035.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00035.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00025-of-00035.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00025-of-00035.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00035.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00026-of-00035.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00026-of-00035.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00035.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00027-of-00035.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00027-of-00035.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00035.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00028-of-00035.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00028-of-00035.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00035.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00029-of-00035.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00029-of-00035.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00035.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00030-of-00035.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00030-of-00035.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00035.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00031-of-00035.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00031-of-00035.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00035.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00032-of-00035.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00032-of-00035.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00035.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00006-of-00035.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00006-of-00035.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00035.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00033-of-00035.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00033-of-00035.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00035.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00034-of-00035.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00034-of-00035.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00035.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00035.bin",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00035.bin",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00035.bin",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00035.bin",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00035.bin",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00035.bin",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00035.bin",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00035.bin",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00035.bin",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00035.bin",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00035.bin",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00035.bin",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00035.bin",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00035.bin",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00035.bin",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00035.bin",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00035.bin",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00035.bin",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 328 |
+
"model.norm.weight": "pytorch_model-00034-of-00035.bin"
|
| 329 |
+
}
|
| 330 |
+
}
|