Upload LlamaForCausalLM
Browse files- config.json +24 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00024.bin +3 -0
- pytorch_model-00002-of-00024.bin +3 -0
- pytorch_model-00003-of-00024.bin +3 -0
- pytorch_model-00004-of-00024.bin +3 -0
- pytorch_model-00005-of-00024.bin +3 -0
- pytorch_model-00006-of-00024.bin +3 -0
- pytorch_model-00007-of-00024.bin +3 -0
- pytorch_model-00008-of-00024.bin +3 -0
- pytorch_model-00009-of-00024.bin +3 -0
- pytorch_model-00010-of-00024.bin +3 -0
- pytorch_model-00011-of-00024.bin +3 -0
- pytorch_model-00012-of-00024.bin +3 -0
- pytorch_model-00013-of-00024.bin +3 -0
- pytorch_model-00014-of-00024.bin +3 -0
- pytorch_model-00015-of-00024.bin +3 -0
- pytorch_model-00016-of-00024.bin +3 -0
- pytorch_model-00017-of-00024.bin +3 -0
- pytorch_model-00018-of-00024.bin +3 -0
- pytorch_model-00019-of-00024.bin +3 -0
- pytorch_model-00020-of-00024.bin +3 -0
- pytorch_model-00021-of-00024.bin +3 -0
- pytorch_model-00022-of-00024.bin +3 -0
- pytorch_model-00023-of-00024.bin +3 -0
- pytorch_model-00024-of-00024.bin +3 -0
- pytorch_model.bin.index.json +330 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "erfanzar/LGeM-7B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 1,
|
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": -1,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "float16",
|
21 |
+
"transformers_version": "4.28.0.dev0",
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 32000
|
24 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.0.dev0"
|
7 |
+
}
|
pytorch_model-00001-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d76207b9f7e4211dbec4a989ffa8e79d3cdf77eec10070355a476dee7f90149
|
3 |
+
size 576720289
|
pytorch_model-00002-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e750f474c73dc7388724278c48b6a02216ee4f8ece9c0902f3f66772bf5bb9e3
|
3 |
+
size 595629999
|
pytorch_model-00003-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac209ba669b5709ce6b7683962c3b84121f8ad11c36e04bc1a12bb25eb6952e8
|
3 |
+
size 528504057
|
pytorch_model-00004-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b44f102affbcef85cc8752f181fe517aad7efd37e7b26933f58b95cf26c3078
|
3 |
+
size 585143563
|
pytorch_model-00005-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25f404c002e16ee244ee738dfeba01204ccdb0bf945c9b3e82ddc66ad12724b7
|
3 |
+
size 538990429
|
pytorch_model-00006-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a5e411f8f2b9827bce167887f18b4628a6a2f5baf18a82b3fc7abbed7425ea9
|
3 |
+
size 585126567
|
pytorch_model-00007-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca4f0cb35da0372f53bda1a4831fac53f0504af38955110e6f9a4cb863e0811a
|
3 |
+
size 595629999
|
pytorch_model-00008-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7f8763dc0247ceba5f2674eea523bd4f345782822726028aa2890358aac96ba
|
3 |
+
size 528504057
|
pytorch_model-00009-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5521db1ace58f784365b5895d759f384d1cb697876e4b14f8700dd4b3e3f151
|
3 |
+
size 585143563
|
pytorch_model-00010-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e1f4e74215a46cbd27101e43b67674d310915c7b9f423c7ea39ebf3e5dabbb5
|
3 |
+
size 538990429
|
pytorch_model-00011-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3215a84aa964facbb05a0aaca1ca1803ea4f209e76d9e5e9ebcb50b87e830667
|
3 |
+
size 585126567
|
pytorch_model-00012-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9770088acd2a74133c8edce0271f6f64db868153f46010b39f9c3db6048bf559
|
3 |
+
size 595629999
|
pytorch_model-00013-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dda4f1bf1437c9618dfc452c92c3a7e6089cd62c98be91e52dfeb13790e5036a
|
3 |
+
size 528504057
|
pytorch_model-00014-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14935753140dc2dda4e7706d7d50ded8d5a03b2e064196e35d20bb513019a5bc
|
3 |
+
size 585143563
|
pytorch_model-00015-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad3b9f7ea22d9875da1e40f3fc4484ad62b13091f9bcf75ea2a6ce0e081033d
|
3 |
+
size 538990429
|
pytorch_model-00016-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe24d5ab0afb7a2732d014eb0813b8b0c91a1c20b702111060967d063ec25dcd
|
3 |
+
size 585126567
|
pytorch_model-00017-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a8741001d1a20ad68e68d1034dfff5a3ab85af36c1dfeb1d23797d4c7483bcc
|
3 |
+
size 595629999
|
pytorch_model-00018-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:251392ff912ddc5fb32f471da11d5a5704c6630bdd0622f92c32e515a7612980
|
3 |
+
size 528504057
|
pytorch_model-00019-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f05ebaa3236077be64db165e0f0057630d58efae6380d41c9f342d49ad4ffab
|
3 |
+
size 585143563
|
pytorch_model-00020-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60d5559a0f96e113e6ae61a6b18a33cc248a1380a47087ea854a2945153d20b6
|
3 |
+
size 538990429
|
pytorch_model-00021-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f528973b4d1b19eca3a236c2c9a345237a9364f737cae72fa729dbbfa5f6998b
|
3 |
+
size 585126567
|
pytorch_model-00022-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:525c439c15ae1c7b55904f2f452c6e1413d3dc4135d477893738da4c188a93e6
|
3 |
+
size 595629999
|
pytorch_model-00023-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a64ede0d472cc9aab1b1dfafde737de929c226c8b7efdaa55798e1de82465548
|
3 |
+
size 528504057
|
pytorch_model-00024-of-00024.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e99e617600cceb37c25f79b6dfa7899ba0ced79c7545d2adaf89877e0543ed7a
|
3 |
+
size 442526143
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476839424
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00024-of-00024.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00024.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00024.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00024.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00024.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00024.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00024.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00024.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00024.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00024.bin",
|
16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00024.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00024.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00024.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00024.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00024.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00024.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00024.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00024.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00024.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00024.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00024.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00024.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00009-of-00024.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00009-of-00024.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00024.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00009-of-00024.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00009-of-00024.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00024.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00024.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00024.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00024.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00024.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00024.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00024.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00024.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00024.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00024.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00009-of-00024.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00009-of-00024.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00009-of-00024.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00024.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00009-of-00024.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00024.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00010-of-00024.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00010-of-00024.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00010-of-00024.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00024.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00010-of-00024.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00010-of-00024.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00010-of-00024.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00024.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00010-of-00024.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00011-of-00024.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00011-of-00024.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00011-of-00024.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00011-of-00024.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00011-of-00024.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00024.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00024.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00024.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00024.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00024.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00012-of-00024.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00024.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00024.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00012-of-00024.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00012-of-00024.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00011-of-00024.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00011-of-00024.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00011-of-00024.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00024.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00011-of-00024.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00024.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00012-of-00024.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00012-of-00024.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00012-of-00024.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00024.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00012-of-00024.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00012-of-00024.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00012-of-00024.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00024.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00012-of-00024.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00013-of-00024.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00013-of-00024.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00013-of-00024.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00013-of-00024.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00013-of-00024.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00024.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00013-of-00024.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00024.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00024.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00024.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00014-of-00024.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00014-of-00024.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00024.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00014-of-00024.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00014-of-00024.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00013-of-00024.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00013-of-00024.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00013-of-00024.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00024.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00013-of-00024.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00024.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00014-of-00024.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00014-of-00024.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00014-of-00024.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00024.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00014-of-00024.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00014-of-00024.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00014-of-00024.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00024.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00014-of-00024.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00015-of-00024.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00015-of-00024.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00015-of-00024.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00015-of-00024.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00015-of-00024.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00015-of-00024.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00015-of-00024.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00015-of-00024.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00024.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00015-of-00024.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00024.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00024.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00024.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00024.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00024.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00024.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00024.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00024.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00024.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00024.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00016-of-00024.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00016-of-00024.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00016-of-00024.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00016-of-00024.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00016-of-00024.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00015-of-00024.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00015-of-00024.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00015-of-00024.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00024.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00015-of-00024.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00017-of-00024.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00016-of-00024.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00016-of-00024.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00017-of-00024.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00017-of-00024.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00016-of-00024.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00016-of-00024.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00016-of-00024.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00024.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00016-of-00024.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00017-of-00024.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00017-of-00024.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00017-of-00024.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00017-of-00024.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00017-of-00024.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00017-of-00024.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00017-of-00024.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00017-of-00024.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00024.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00017-of-00024.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00018-of-00024.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00018-of-00024.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00018-of-00024.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00018-of-00024.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00018-of-00024.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00017-of-00024.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00018-of-00024.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00017-of-00024.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00024.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00017-of-00024.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00019-of-00024.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00019-of-00024.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00018-of-00024.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00019-of-00024.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00019-of-00024.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00018-of-00024.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00018-of-00024.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00018-of-00024.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00024.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00018-of-00024.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00019-of-00024.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00019-of-00024.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00019-of-00024.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00019-of-00024.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00019-of-00024.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00019-of-00024.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00019-of-00024.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00019-of-00024.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00024.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00019-of-00024.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00020-of-00024.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00020-of-00024.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00020-of-00024.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00020-of-00024.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00020-of-00024.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00020-of-00024.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00020-of-00024.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00020-of-00024.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00024.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00020-of-00024.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00021-of-00024.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00021-of-00024.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00021-of-00024.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00021-of-00024.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00021-of-00024.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00020-of-00024.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00020-of-00024.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00020-of-00024.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00024.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00020-of-00024.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00022-of-00024.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00021-of-00024.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00021-of-00024.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00022-of-00024.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00022-of-00024.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00021-of-00024.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00021-of-00024.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00021-of-00024.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00024.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00021-of-00024.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00022-of-00024.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00022-of-00024.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00022-of-00024.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00022-of-00024.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00022-of-00024.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00022-of-00024.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00022-of-00024.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00022-of-00024.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00024.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00022-of-00024.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00024.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00024.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00024.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00024.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00024.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00024.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00024.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00024.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00024.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00024.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00023-of-00024.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00023-of-00024.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00023-of-00024.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00023-of-00024.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00023-of-00024.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00022-of-00024.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00023-of-00024.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00022-of-00024.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00024.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00022-of-00024.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00024-of-00024.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00024-of-00024.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00023-of-00024.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00024-of-00024.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00024-of-00024.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00023-of-00024.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00023-of-00024.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00023-of-00024.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00024.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00023-of-00024.bin",
|
268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00024.bin",
|
269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00024.bin",
|
270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00024.bin",
|
271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00024.bin",
|
272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00024.bin",
|
273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00024.bin",
|
274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00024.bin",
|
275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00024.bin",
|
276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00024.bin",
|
277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00024.bin",
|
278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00024.bin",
|
279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00024.bin",
|
280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00024.bin",
|
281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00024.bin",
|
282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00024.bin",
|
283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00005-of-00024.bin",
|
284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00005-of-00024.bin",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00005-of-00024.bin",
|
286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00024.bin",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00005-of-00024.bin",
|
288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00024.bin",
|
289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00024.bin",
|
290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00006-of-00024.bin",
|
291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00006-of-00024.bin",
|
292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00024.bin",
|
293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00024.bin",
|
294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00024.bin",
|
295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00024.bin",
|
296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00024.bin",
|
297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00024.bin",
|
298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00007-of-00024.bin",
|
299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00024.bin",
|
300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00024.bin",
|
301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00007-of-00024.bin",
|
302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00007-of-00024.bin",
|
303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00024.bin",
|
304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00024.bin",
|
305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00024.bin",
|
306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00024.bin",
|
307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00024.bin",
|
308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00024.bin",
|
309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00024.bin",
|
310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00024.bin",
|
311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00024.bin",
|
312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00024.bin",
|
313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00007-of-00024.bin",
|
314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00007-of-00024.bin",
|
315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00007-of-00024.bin",
|
316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00024.bin",
|
317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00007-of-00024.bin",
|
318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00024.bin",
|
319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00008-of-00024.bin",
|
320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00008-of-00024.bin",
|
321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00008-of-00024.bin",
|
322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00024.bin",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00024.bin",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00008-of-00024.bin",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00024.bin",
|
326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00024.bin",
|
327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00024.bin",
|
328 |
+
"model.norm.weight": "pytorch_model-00024-of-00024.bin"
|
329 |
+
}
|
330 |
+
}
|