huihui-ai commited on
Commit
e2618c3
1 Parent(s): 4c66442

Upload 21 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,45 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ library_name: transformers
4
+ language:
5
+ - en
6
+ - fr
7
+ - de
8
+ - es
9
+ - it
10
+ - pt
11
+ - ja
12
+ - ko
13
+ - zh
14
+ - ar
15
+ - el
16
+ - fa
17
+ - pl
18
+ - id
19
+ - cs
20
+ - he
21
+ - hi
22
+ - nl
23
+ - ro
24
+ - ru
25
+ - tr
26
+ - uk
27
+ - vi
28
+ license: cc-by-nc-4.0
29
+ extra_gated_prompt: "By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and acknowledge that the information you provide will be collected, used, and shared in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll receive email updates about C4AI and Cohere research, events, products and services. You can unsubscribe at any time."
30
+ extra_gated_fields:
31
+ Name: text
32
+ Affiliation: text
33
+ Country: country
34
+ I agree to use this model for non-commercial use ONLY: checkbox
35
+ tags:
36
+ - abliterated
37
+ - uncensored
38
+ ---
39
+
40
+ # huihui-ai/aya-expanse-32b-abliterated
41
+
42
+
43
+ This is an uncensored version of [CohereForAI/aya-expanse-32b](https://huggingface.co/CohereForAI/aya-expanse-32b) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
44
+ This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
45
+
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CohereForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 5,
8
+ "eos_token_id": 255001,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 24576,
13
+ "layer_norm_eps": 1e-05,
14
+ "logit_scale": 0.0625,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "cohere",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 40,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 0,
21
+ "rope_theta": 4000000,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.44.0",
24
+ "use_cache": true,
25
+ "use_qk_norm": false,
26
+ "vocab_size": 256000
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "eos_token_id": 255001,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.0"
7
+ }
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0cf8d0a3a10fb0f16a2901d7e41435aee0ae6348b92350b57cc06f7d30bd6b
3
+ size 4898947792
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70cdff96107111c4839e0cde2597fad4db6939221b75f82de4b887ded8eca7ae
3
+ size 4932553552
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5008bcf8d45f8df74a51b2ba82150a74d1f2506d57eb9798c4f6eac5c55d89
3
+ size 4932570048
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f77b357165ad305e601fe841cc7f5b223cd5fc44cc47e99f8443a47d3c40b4
3
+ size 4831890616
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2560853dcc135924148cffb5784a63f8977b3ccbb755da05d24f427dc5d20444
3
+ size 4932553584
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cce1c9d38fcc88f03c38603df162e9b2ec15fcca93d2ffe7c96c54c531a71c3
3
+ size 4932553576
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6afa858ddf88937a87eb8251eeb3793c95fa4b2fcc0a24fa11c2a6e1abe658
3
+ size 4932570080
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a45e7254380634cd09a6c1619286ad5917c9ec14b7170b9ffe4bfcb7edf402
3
+ size 4831890640
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5d0cd25c0350851167e9101b652fab57affb2632f15e5164291dcd7a1bb139
3
+ size 4932553584
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ceca876d64d0f9e44af071f3497a67e7aa2d79174d2af2e2aff3ab693b5034
3
+ size 4932553576
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f50f189831c7a9a4e4493a6326828c601eea6641d1a083cbd8752b847c7361
3
+ size 4932570080
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3366a32b9a424697ab160bc083b0fe768c25b3a79ee781c09f2550be76afdfa1
3
+ size 4831890640
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed9bea14aae53465481a3f539a57a5e1867208efb0126fd463c95b68cd006e1
3
+ size 4932553584
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3cf8aacd82b81395113f267714950b1f555c01cce9bf2881100d20986aa4b45
3
+ size 805339592
model.safetensors.index.json ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 64592953344
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00014.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
11
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
16
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
17
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
18
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
19
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
20
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
21
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
22
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
23
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors",
24
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
25
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
26
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
27
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
28
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
29
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
30
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
31
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors",
32
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
33
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
34
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
35
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
36
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
37
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
38
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
39
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
40
+ "model.layers.12.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
41
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
42
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
43
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
44
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
45
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
46
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
47
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00014.safetensors",
48
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
49
+ "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
50
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
51
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
52
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
53
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
54
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
55
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors",
56
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
57
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
58
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
59
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
60
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
61
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
62
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
63
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
64
+ "model.layers.15.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
65
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
66
+ "model.layers.15.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
67
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
68
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
69
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
70
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
71
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors",
72
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
73
+ "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
74
+ "model.layers.16.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
75
+ "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
76
+ "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
77
+ "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
78
+ "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
79
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00014.safetensors",
80
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
81
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
82
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
83
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
84
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
85
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
86
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
87
+ "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
88
+ "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
89
+ "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
90
+ "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
91
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
92
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
93
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
94
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
95
+ "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
96
+ "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
97
+ "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
98
+ "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
99
+ "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
100
+ "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
101
+ "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
102
+ "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
103
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
104
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
105
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
106
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
107
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
108
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
109
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
110
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
111
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00014.safetensors",
112
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
113
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
114
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
115
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
116
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
117
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
118
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
119
+ "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
120
+ "model.layers.21.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
121
+ "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
122
+ "model.layers.21.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
123
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
124
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
125
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
126
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
127
+ "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
128
+ "model.layers.22.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
129
+ "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
130
+ "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
131
+ "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
132
+ "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
133
+ "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
134
+ "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
135
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors",
136
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
137
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
138
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
139
+ "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
140
+ "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
141
+ "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
142
+ "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
143
+ "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
144
+ "model.layers.24.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
145
+ "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
146
+ "model.layers.24.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
147
+ "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
148
+ "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
149
+ "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
150
+ "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
151
+ "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
152
+ "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
153
+ "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
154
+ "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
155
+ "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
156
+ "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
157
+ "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
158
+ "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
159
+ "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors",
160
+ "model.layers.26.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
161
+ "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
162
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
163
+ "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
164
+ "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
165
+ "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
166
+ "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
167
+ "model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
168
+ "model.layers.27.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
169
+ "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
170
+ "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
171
+ "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
172
+ "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
173
+ "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
174
+ "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
175
+ "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
176
+ "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
177
+ "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
178
+ "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
179
+ "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
180
+ "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
181
+ "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
182
+ "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
183
+ "model.layers.29.input_layernorm.weight": "model-00011-of-00014.safetensors",
184
+ "model.layers.29.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
185
+ "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
186
+ "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
187
+ "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
188
+ "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
189
+ "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
190
+ "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
191
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00014.safetensors",
192
+ "model.layers.3.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
193
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
194
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
195
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
196
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
197
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
198
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
199
+ "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
200
+ "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
201
+ "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
202
+ "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
203
+ "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
204
+ "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
205
+ "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
206
+ "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
207
+ "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
208
+ "model.layers.31.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
209
+ "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
210
+ "model.layers.31.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
211
+ "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
212
+ "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
213
+ "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
214
+ "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
215
+ "model.layers.32.input_layernorm.weight": "model-00011-of-00014.safetensors",
216
+ "model.layers.32.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
217
+ "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
218
+ "model.layers.32.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
219
+ "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
220
+ "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
221
+ "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
222
+ "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
223
+ "model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
224
+ "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
225
+ "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
226
+ "model.layers.33.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
227
+ "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
228
+ "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
229
+ "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
230
+ "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
231
+ "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
232
+ "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
233
+ "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
234
+ "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
235
+ "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
236
+ "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
237
+ "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
238
+ "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
239
+ "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors",
240
+ "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
241
+ "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
242
+ "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
243
+ "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
244
+ "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
245
+ "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
246
+ "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
247
+ "model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
248
+ "model.layers.36.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
249
+ "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
250
+ "model.layers.36.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
251
+ "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
252
+ "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
253
+ "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
254
+ "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
255
+ "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
256
+ "model.layers.37.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
257
+ "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
258
+ "model.layers.37.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
259
+ "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
260
+ "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
261
+ "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
262
+ "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
263
+ "model.layers.38.input_layernorm.weight": "model-00013-of-00014.safetensors",
264
+ "model.layers.38.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
265
+ "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
266
+ "model.layers.38.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
267
+ "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
268
+ "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
269
+ "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
270
+ "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
271
+ "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
272
+ "model.layers.39.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
273
+ "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
274
+ "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
275
+ "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
276
+ "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
277
+ "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
278
+ "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
279
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00014.safetensors",
280
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
281
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
282
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
283
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
284
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
285
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
286
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
287
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
288
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
289
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
290
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
294
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
295
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
296
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
297
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
298
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
299
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
300
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
301
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
302
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
303
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors",
304
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
305
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
306
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
307
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
308
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
309
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
310
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
311
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
312
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
313
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
314
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
315
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
316
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
317
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
318
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
319
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
320
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
321
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
322
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
323
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
324
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
325
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
326
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
327
+ "model.norm.weight": "model-00014-of-00014.safetensors"
328
+ }
329
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<BOS_TOKEN>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|END_OF_TURN_TOKEN|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<PAD>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345ccf04a5257f473e331715ecc69365c5ac8fc2490923fe7155560af809ec1a
3
+ size 20124090
tokenizer_config.json ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<PAD>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<UNK>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<CLS>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<SEP>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<MASK_TOKEN>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<BOS_TOKEN>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<EOS_TOKEN>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<EOP_TOKEN>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "255000": {
71
+ "content": "<|START_OF_TURN_TOKEN|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "255001": {
79
+ "content": "<|END_OF_TURN_TOKEN|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "255002": {
87
+ "content": "<|YES_TOKEN|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "255003": {
95
+ "content": "<|NO_TOKEN|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "255004": {
103
+ "content": "<|GOOD_TOKEN|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "255005": {
111
+ "content": "<|BAD_TOKEN|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "255006": {
119
+ "content": "<|USER_TOKEN|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "255007": {
127
+ "content": "<|CHATBOT_TOKEN|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "255008": {
135
+ "content": "<|SYSTEM_TOKEN|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "255009": {
143
+ "content": "<|USER_0_TOKEN|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "255010": {
151
+ "content": "<|USER_1_TOKEN|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "255011": {
159
+ "content": "<|USER_2_TOKEN|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "255012": {
167
+ "content": "<|USER_3_TOKEN|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "255013": {
175
+ "content": "<|USER_4_TOKEN|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "255014": {
183
+ "content": "<|USER_5_TOKEN|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "255015": {
191
+ "content": "<|USER_6_TOKEN|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "255016": {
199
+ "content": "<|USER_7_TOKEN|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "255017": {
207
+ "content": "<|USER_8_TOKEN|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "255018": {
215
+ "content": "<|USER_9_TOKEN|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "255019": {
223
+ "content": "<|EXTRA_0_TOKEN|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "255020": {
231
+ "content": "<|EXTRA_1_TOKEN|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "255021": {
239
+ "content": "<|EXTRA_2_TOKEN|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "255022": {
247
+ "content": "<|EXTRA_3_TOKEN|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "255023": {
255
+ "content": "<|EXTRA_4_TOKEN|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "255024": {
263
+ "content": "<|EXTRA_5_TOKEN|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "255025": {
271
+ "content": "<|EXTRA_6_TOKEN|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "255026": {
279
+ "content": "<|EXTRA_7_TOKEN|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "255027": {
287
+ "content": "<|EXTRA_8_TOKEN|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "255028": {
295
+ "content": "<|EXTRA_9_TOKEN|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": false
301
+ }
302
+ },
303
+ "bos_token": "<BOS_TOKEN>",
304
+ "chat_template": [
305
+ {
306
+ "name": "default",
307
+ "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by providing thorough responses. You are able to interact and respond to questions in 23 languages and you are powered by a multilingual model built by Cohere For AI.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
308
+ }
309
+ ],
310
+ "clean_up_tokenization_spaces": false,
311
+ "eos_token": "<|END_OF_TURN_TOKEN|>",
312
+ "extra_special_tokens": {},
313
+ "legacy": true,
314
+ "merges_file": null,
315
+ "model_max_length": 1000000000000000019884624838656,
316
+ "pad_token": "<PAD>",
317
+ "sp_model_kwargs": {},
318
+ "spaces_between_special_tokens": false,
319
+ "tokenizer_class": "CohereTokenizer",
320
+ "unk_token": null,
321
+ "use_default_system_prompt": false,
322
+ "vocab_file": null
323
+ }