pskun commited on
Commit
73146ce
1 Parent(s): 259ee62

Upload folder using huggingface_hub (#1)

Browse files

- 9a0b9e713efae85fe867a16758255a8578361de9fa864b0178966f3c0e737ebc (b753316d06498382a89ac89c4b6080b4cb4cdb24)
- 4cb081733a6c3aeb6ba8ae8e27e2f9f4d44d9dc41829640f04e33892a31a0c6f (98a094e6653666fb47603389455466dc5c37f8c1)
- 523bc53eefd031e448c1fb334669acd02f15fabe367a65550115af77c1208948 (ba42a21ebb991412ff861058513a1f1504134417)
- f03558fdd577314823b40c398fa2ffc396886f2396cf7f7e29cfc526daa72d6e (120900d1e0ac2ef46b3742a48065913f703685b4)
- f2bad7f4a2fbf90ed4813c047445e87e3c38c5516b8fdb101e038e115e8b8c40 (41a44cffe4dcafb66e6e7e0d56d7a4efb2ce4e9a)
- 3d5eff006a763f4efdd5f2c722324855739a8d2ffcaf89992df306cffe0ae12a (e627e8dee992c0acba7282d7b50a2590fd898c57)
- eac55e9a88b7635538c7ec85d86b72eb7124ba3e6a05daab208a97e170ef0f0c (955351658b402fdcfc4f6c0d8306c500cb21c3f2)
- e76206c54521f702c4bd6bd3d75e706e0712ec7875b0c741334b36d9819db629 (2cee8a4aa4a92c93f19ebfc308750feeeef2d9a2)
- 344f8a2f8974a56715977ad9c533133efe4c83b432c6612656a86e669ecdfe2f (29ac2de19117a381e8910eb603e18c708c1787cd)
- 8f3e842ecdfe2592216165b952b3f9c70c1f2bba50b10c058871136b4a606a4b (de459ffa79c66df1656ab7376d55d594126f4c18)
- fe220c959a8e4ed9ea56b599ea0ea83c6258f92c61d4d08586a707ab204bfbd7 (2ea3fbb252a8f3cdebfa4e5ade33e057f1e71f5a)
- 36d3b063c07b2ce947f9a2a122326880e4fc76c97e4b4b53826bf3a16c8e6abf (c17baee1f7dee58417974159e435fa82441f3b4b)
- 8270bfa5db1efb5b764698e2a48156048008f7e988de273f45782c909b6ade6c (997d3f7fc5838baf6f5951f938dac91f1a33b760)
- 831aec39d69c87329ade7b2633ff1cf7afe7cee8c18f2e948674adcb7b1e84cc (283b03a100b5baf603b2077b7ba480e272e7fdf2)
- 0a71474b008e16e9b5eb1b2618dfddee4083adc9dc701d6f151e9849cf5c2474 (a963fc2d4fca843aa957b3c99ac50cc18b603933)
- 19397c6932049d9a8aa4080b159bee4a4fe5836193f93b745b16b9760334a782 (3413f5330f7cc52eafae6d017eb6be45dcb76185)
- 580cdfb6c68b44782fc48c8fc873b7821b12fd7bddd2e8a929605215804fd015 (9c6bfbacd65abac83a4e3c59c556212a63f9d95c)
- d31de7a9e72f1a21e8a8fe670a55fbdcb26dea57fe93988b29933e3c9405cfcb (5c2c2ad6c771ab713c81f040ebab6ef8824ff1a3)
- 05ee13e84be11facd6fe44f1b056753431603075e42bb54b76ea3526e303a198 (b878b7248cd04512b91909ea91d37c819245d659)

config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Ziya-Writing-13B-v1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 1,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
24
+ "use_cache": false,
25
+ "use_parallel_residual": false,
26
+ "vocab_size": 39424
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.30.2"
7
+ }
pytorch_model-00001-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec33896da438c959c1678f34d52aa74ee4880b1f096a4f1fa1fd29758dbc56f
3
+ size 2778773825
pytorch_model-00002-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835797c5b52ffacdd8301b60c2144d5e0d94ecd54e2a90e5cb6be0ee5a9f3358
3
+ size 2820759049
pytorch_model-00003-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:538a7f3384ca5d5089c199d70b04b78e41c26a9463e48bac90399edd3351f0eb
3
+ size 2925658559
pytorch_model-00004-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48b21a9d5b7a2e485aa75e0cc0cb02b03f4f7b219b574c271b892253e03bdf7
3
+ size 2852217535
pytorch_model-00005-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fd8d5d39030a6456eb803e5180705e38a86338d413c9e03713714c3b380642
3
+ size 2820759049
pytorch_model-00006-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f71bc6829964fd160778d124ecffe444fcbd143a9c6b57f983a673df965be78
3
+ size 2820759049
pytorch_model-00007-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ced14dbc9445e1a9ad0351f3d77f5a4fcef3c9b37e287cd08d53822b107662c3
3
+ size 2925658559
pytorch_model-00008-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b3be835159714808f72adaf484c5505dde41daa9ea89044e9df215c519cf3f
3
+ size 2852217535
pytorch_model-00009-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70991c6dc933260d93db64ae1354bd657e83522403a20735177e06daf8b86245
3
+ size 2820759049
pytorch_model-00010-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2296ade2da137db6ac680c261daa891d40b67b16c838510c20ad74674722de4d
3
+ size 2820759049
pytorch_model-00011-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c64c86a4e2308c1439f54f66c8ba869c54541284d279c291390719439e5c5a
3
+ size 2925658559
pytorch_model-00012-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1238b462ac11633cecce1c7353001a729432d3132df525367f6d30c86ddada
3
+ size 2852217535
pytorch_model-00013-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587bff335a3c0f082a24d1d373a8a81aae1237e78ae08e8a8a74874091fc2cda
3
+ size 2820759049
pytorch_model-00014-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0bcb7f2fe588c7da18bcf324f33bcc0be9da33f688ab2e4045d592f3966a465
3
+ size 2820759049
pytorch_model-00015-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d35a473866d7d22a2b70d6e4e3c90efbd9e414211703c9cec124fe7f964979
3
+ size 2925658559
pytorch_model-00016-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a23288b26590fb341e1ae858ffb7f74000a364aeab811a42e514d7528be1967f
3
+ size 2852217535
pytorch_model-00017-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a3311f2535c08ec72214b89d4fb976d4ec468553e7953f6f6a682a311e0b1e
3
+ size 2820759049
pytorch_model-00018-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11a3899ebb62971fa6be301f5efe989ed46dedbc34968ecb6f10a54b110e2f4
3
+ size 2820759049
pytorch_model-00019-of-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4565877a6f050ac4ea04d146b9e9aeb4e83600e5323da3cb365d731b562fd43
3
+ size 1090582638
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 52367554560
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00019-of-00019.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00019.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00019.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00019.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00019.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00019.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00019.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00019.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00019.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00019.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00019.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00006-of-00019.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00019.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00019.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00019.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00019.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00019.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00019.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00019.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00019.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00019.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00019.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00008-of-00019.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00019.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00019.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00019.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00019.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00019.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00009-of-00019.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00019.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00019.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00019.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00010-of-00019.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00019.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00019.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00019.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00019.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00010-of-00019.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00019.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00019.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00019.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00019.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00011-of-00019.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00019.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00019.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00019.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00012-of-00019.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00012-of-00019.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00019.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00019.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00019.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00019.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00013-of-00019.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00019.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00019.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00019.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00014-of-00019.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00019.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00014-of-00019.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00014-of-00019.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00019.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00019.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00019.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00019.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00019.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00015-of-00019.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00019.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00015-of-00019.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00019.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00016-of-00019.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00016-of-00019.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00019.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00016-of-00019.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00016-of-00019.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00019.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00017-of-00019.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00019.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00017-of-00019.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00019.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00018-of-00019.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00019.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00018-of-00019.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00018-of-00019.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00019.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00019-of-00019.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00018-of-00019.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00019-of-00019.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00019.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00019.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00019.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00019.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00019.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00019.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00019.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00019.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00019.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00019.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00019.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00019.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00019.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00019.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00019.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin",
408
+ "model.norm.weight": "pytorch_model-00019-of-00019.bin"
409
+ }
410
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147fa8ef9267d7760a39e07a15eeadb64ce6560a74fa92f4e69cf206307e876c
3
+ size 588649
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "padding_side": "right",
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }