Hugging Face's logo

sambanovasystems
/
LLaMA-30b-toolbench

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
3
bol20162021 commited on
Commit
3b0ac8e
•
1 Parent(s): 34d4335

Upload folder using huggingface_hub (#2)

Browse files

- c1aa5e558b2661504ccbf83398a6bfc09c9a6b2e93d6c4628885d9adb1abf9b0 (6f77566afb3bd84939420a6a72af3887193323db)
- c2f9dfb4298681d31a12b0a803b210f3d35cfc6959f6af1e907efbb3a5343a9d (6b634bcbafecb156e64b45482ae2c73366f428d2)
- 96c9f4f9eb91892142683f467e256c0abfcc5f22c11d0ac69e4050dbf40ebefc (9d05206203101d6c560d0ddefd7b1c489f68c50b)
- f34abfa4176269e3169fe4ce67d2a7bfb998779517b124adccc08928b37bf726 (f7ad8eebef4c0fe20218c5745e045618b0481f02)
- 7415d9e41bc5468cb4390dbccce50b540ae3ea7309fed575b7b84b8a234eca6b (805f4d75076b58c5fc769d2d7546755cd1f088bc)
- ddf8697d26b854ab2f1a4537a3ade65ee774b192ad1b124ef3e7bfd15dd74ce3 (e4f486f8fc116f7f7061dc15b71d7105f9698c28)
- 4e9c129425bafcf80b1cf6495182f51bc8b5889cc9baa9cdb10707d51eb40e4b (0f7648d90696cf89611dea179e28aace478b8748)
- fb001862f59a56063b2db2995eaf3cef78c644b4cb74c9d1a473f43096c8ea23 (797069a120e88cbfaa475ba582a98d97684e8e9e)
- 25b24f35d6c0f8064af558dd66d1c9eb205de1eca75b45fcf861ac81d1f6c604 (197060f90c15deb53998369803212e7265772b73)
- daa927a3a13f76a47893b9cd58b83aa903ab327ecf0d09bc80e3da90f3c7d0f0 (50cba38ca06da8c85dba904c0f54a3a889f05327)
- 7a52e6a6bac3ecbad97a60723cd271fff787b61509dedf5c808ddb707c21deee (84403fc0aa426f3d033e8569b1d94389e397b8c9)
- 3ecf9470cc96ce7d306b80b6d5118f048161979fa35f612037525e5e7839e550 (dde37330cfd0951c525eb6c1a5a2729a0c4322ab)
- bba6680665283c8756679f559c4fd82666572165dfcc37babb28e24ed23869aa (58708f0d98b95cab1a82659e1915e5a71818f348)
- 16cc9aa8fe537208a3a14f16c49037e4256cd1c384d3a5d075c4a2e78f6699b9 (f9f64d84fd519f967f3b037acb3c9342c54b0a78)
- e52443de962faefc723fbeb20d634b65c0c1b21483a9597996eb17453d6ae260 (281b1ba179f12a7433e4b6a3d5aa5bf1dd4aa2a1)

Files changed (20) hide show
  1. config.json +24 -0
  2. generation_config.json +7 -0
  3. pytorch_model-00001-of-00014.bin +3 -0
  4. pytorch_model-00002-of-00014.bin +3 -0
  5. pytorch_model-00003-of-00014.bin +3 -0
  6. pytorch_model-00004-of-00014.bin +3 -0
  7. pytorch_model-00005-of-00014.bin +3 -0
  8. pytorch_model-00006-of-00014.bin +3 -0
  9. pytorch_model-00007-of-00014.bin +3 -0
  10. pytorch_model-00008-of-00014.bin +3 -0
  11. pytorch_model-00009-of-00014.bin +3 -0
  12. pytorch_model-00010-of-00014.bin +3 -0
  13. pytorch_model-00011-of-00014.bin +3 -0
  14. pytorch_model-00012-of-00014.bin +3 -0
  15. pytorch_model-00013-of-00014.bin +3 -0
  16. pytorch_model-00014-of-00014.bin +3 -0
  17. pytorch_model.bin.index.json +610 -0
  18. special_tokens_map.json +23 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +33 -0
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sambanovasystems/LLaMA-30B-toolbench",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 6656,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 17920,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 52,
16
+ "num_hidden_layers": 60,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.29.0",
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": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.29.0"
7
+ }
pytorch_model-00001-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee40aaaaa537eabc8edfd7264f32c3759fb24620e926c1811be00c864b545f1b
3
+ size 9944399515
pytorch_model-00002-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325d9f95a01e9a3922fdbbee254fff9d58b38629be9325c545c7ed02b05a21d5
3
+ size 9692217267
pytorch_model-00003-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753682a8336b12884e51b987082fbdb5f3651c240ad28c9680b3e749def35236
3
+ size 9746797807
pytorch_model-00004-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303c10ae13777600aac71f857a408e8e549c785e79f030c7e3f9a28dd19a45d5
3
+ size 9992163381
pytorch_model-00005-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd061cd37f603169e875337c20a14e3d46609a19e88e05b7daa7d3cbd4f0df31
3
+ size 9746743895
pytorch_model-00006-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:588279fc2406c614f4e41bc3e64b44746e37c5ea6db1867797968adb7e24b5cb
3
+ size 9869480291
pytorch_model-00007-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a28e676b5d066aa5de4c3ae476ee1d52014b145deb1cb8a42b85065223993e6f
3
+ size 9869426913
pytorch_model-00008-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b017055afdbc1a585889315e81e6c31017ba4c065e92bdf93cb87ed7cc21b78
3
+ size 9746797807
pytorch_model-00009-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7baa5d6fee88d6b4773baf6d68be8e054eb07fcba364c40f13fc33d27ec3e6ee
3
+ size 9992163381
pytorch_model-00010-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3142af2bd2931a5769658990ced31d8d5d1d544fe8a68448d483291b0057adb8
3
+ size 9746743895
pytorch_model-00011-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b26e67d393f7d48f7521af73ba785b1cb13d54ca403081d1be8c57c7fe1c959
3
+ size 9869480291
pytorch_model-00012-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3b20d11da6176a4150323755b885ea812ef8240e317b1f6a0dda2848c74030
3
+ size 9869426913
pytorch_model-00013-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70528696b79ff7c29261a7012b3a24661c27c5a536f88b8f051e7e8dac528274
3
+ size 9746797807
pytorch_model-00014-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7a2c276bebcfbddace97d7d4b7418124ed656cd7102ae99cecc021663013a7
3
+ size 2283356880
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,610 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 130115789824
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00014-of-00014.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
358
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
359
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
360
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
361
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
362
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
363
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
364
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
365
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
366
+ "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
367
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
368
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
369
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
370
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
371
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
372
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
373
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
374
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
375
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
376
+ "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
377
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
378
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
379
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
380
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
381
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
382
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
383
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
384
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
385
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
386
+ "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
387
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
388
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
389
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
390
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
391
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
392
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
393
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
394
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
395
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
396
+ "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
397
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
398
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
399
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
400
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
401
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
402
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
403
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
404
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
405
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
406
+ "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
407
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
408
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
409
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
410
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
411
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
412
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
413
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
414
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
415
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
416
+ "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
417
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
418
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
419
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
420
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
421
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
422
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
423
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
424
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
425
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
426
+ "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
427
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
428
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
429
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
430
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
431
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
432
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
433
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
434
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
435
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
436
+ "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
437
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
438
+ "model.layers.48.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
439
+ "model.layers.48.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
440
+ "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
441
+ "model.layers.48.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
442
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
443
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
444
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
445
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
446
+ "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
447
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
448
+ "model.layers.49.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
449
+ "model.layers.49.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
450
+ "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
451
+ "model.layers.49.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
452
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
453
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
454
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
455
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
456
+ "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
457
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
458
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
459
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
460
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
461
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
462
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
463
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
464
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
465
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
466
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
467
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
468
+ "model.layers.50.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
469
+ "model.layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
470
+ "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
471
+ "model.layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
472
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
473
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
474
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
475
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
476
+ "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
477
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
478
+ "model.layers.51.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
479
+ "model.layers.51.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
480
+ "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
481
+ "model.layers.51.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
482
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
483
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
484
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
485
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
486
+ "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
487
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
488
+ "model.layers.52.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
489
+ "model.layers.52.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
490
+ "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
491
+ "model.layers.52.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
492
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
493
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
494
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
495
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
496
+ "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
497
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
498
+ "model.layers.53.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
499
+ "model.layers.53.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
500
+ "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
501
+ "model.layers.53.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
502
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
503
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
504
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
505
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
506
+ "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
507
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
508
+ "model.layers.54.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
509
+ "model.layers.54.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
510
+ "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
511
+ "model.layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
512
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
513
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
514
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
515
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
516
+ "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
517
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
518
+ "model.layers.55.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
519
+ "model.layers.55.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
520
+ "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
521
+ "model.layers.55.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
522
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
523
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
524
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
525
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
526
+ "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
527
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
528
+ "model.layers.56.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
529
+ "model.layers.56.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
530
+ "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
531
+ "model.layers.56.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
532
+ "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
533
+ "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
534
+ "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
535
+ "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
536
+ "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
537
+ "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
538
+ "model.layers.57.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
539
+ "model.layers.57.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
540
+ "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
541
+ "model.layers.57.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
542
+ "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
543
+ "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
544
+ "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
545
+ "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
546
+ "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
547
+ "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
548
+ "model.layers.58.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
549
+ "model.layers.58.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
550
+ "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
551
+ "model.layers.58.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
552
+ "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
553
+ "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
554
+ "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
555
+ "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
556
+ "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
557
+ "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
558
+ "model.layers.59.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
559
+ "model.layers.59.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
560
+ "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
561
+ "model.layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
562
+ "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
563
+ "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
564
+ "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
565
+ "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
566
+ "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
567
+ "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
568
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
569
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
570
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
571
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
572
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
573
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
574
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
575
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
576
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
577
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
578
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
579
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
580
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
581
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
582
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
583
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
584
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
585
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
586
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
587
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
588
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
589
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
590
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
591
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
592
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
593
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
594
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
595
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
596
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
597
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
598
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
599
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
600
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
601
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
602
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
603
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
604
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
605
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
606
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
607
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
608
+ "model.norm.weight": "pytorch_model-00014-of-00014.bin"
609
+ }
610
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }