prince-canuma commited on
Commit
0633ee2
1 Parent(s): 65e49d2

Upload folder using huggingface_hub (#1)

Browse files

- 2949400f36ca140209643157e816beb1a3c50f6420743a66bfbb6d4b4ff3e03d (3a8fafbe5828e1dd29bb75f2ca03ca59a8b5c20f)
- 18884201032f10e3dcb39e0cceb42a97b180f232a4195a793faa2c4a63a5fcd6 (607ba4e61cb416b1debaa43ad1947296c08e6d79)
- a3683bc12fac91c45ddf63bb98f9f79b596692e8f8d23b902b0f74c2a17654b1 (c956faef84ad39e0e39029dc7db83170e18b101c)

.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 ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - fr
5
+ - de
6
+ - es
7
+ - it
8
+ - pt
9
+ - ja
10
+ - ko
11
+ - zh
12
+ - ar
13
+ - el
14
+ - fa
15
+ - pl
16
+ - id
17
+ - cs
18
+ - he
19
+ - hi
20
+ - nl
21
+ - ro
22
+ - ru
23
+ - tr
24
+ - uk
25
+ - vi
26
+ license: cc-by-nc-4.0
27
+ library_name: transformers
28
+ tags:
29
+ - mlx
30
+ ---
31
+
32
+ # mlx-community/aya-23-8B-8bit
33
+
34
+ The Model [mlx-community/aya-23-8B-8bit](https://huggingface.co/mlx-community/aya-23-8B-8bit) was converted to MLX format from [CohereForAI/aya-23-8B](https://huggingface.co/CohereForAI/aya-23-8B) using mlx-lm version **0.13.1**.
35
+
36
+ ## Use with mlx
37
+
38
+ ```bash
39
+ pip install mlx-lm
40
+ ```
41
+
42
+ ```python
43
+ from mlx_lm import load, generate
44
+
45
+ model, tokenizer = load("mlx-community/aya-23-8B-8bit")
46
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
47
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "layer_norm_eps": 1e-05,
14
+ "logit_scale": 0.0625,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "cohere",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 0,
21
+ "quantization": {
22
+ "group_size": 64,
23
+ "bits": 8
24
+ },
25
+ "rope_theta": 10000,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.40.0.dev0",
28
+ "use_cache": true,
29
+ "use_qk_norm": false,
30
+ "vocab_size": 256000
31
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c19d49a49e52a59d87df9fd3770628d278de3c667b3ec5549ab3c361a4a3e1f
3
+ size 5330105819
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705e692d566c95c7827c94d08f1e9af3c34afd2a7a0cf2ef18f8ab55c05eef9d
3
+ size 3199886266
model.safetensors.index.json ADDED
@@ -0,0 +1,715 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8529911808
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
7
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
55
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
56
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
58
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
59
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
61
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
64
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
65
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
67
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
68
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
70
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
71
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
77
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
78
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
80
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
81
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
83
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
84
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
86
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
87
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
89
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
90
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
92
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
93
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
95
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
96
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
99
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
100
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
102
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
103
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
105
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
106
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
108
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
109
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
111
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
112
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
114
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
115
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
117
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
118
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
121
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
122
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
124
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
125
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
127
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
128
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
130
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
131
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
133
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
134
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
136
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
137
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
139
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
140
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
143
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
144
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
146
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
147
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
149
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
150
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
152
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
153
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
155
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
156
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
158
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
159
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
161
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
162
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
165
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
166
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
168
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
169
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
171
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
172
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
174
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
175
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
177
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
178
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
180
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
181
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
183
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
184
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
187
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
188
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
190
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
191
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
193
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
194
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
196
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
197
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
199
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
200
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
202
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
203
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
205
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
206
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
209
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
210
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
212
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
213
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
215
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
216
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
218
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
219
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
221
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
222
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
224
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
225
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
227
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
228
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
231
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
232
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
234
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
235
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
237
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
238
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
240
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
241
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
243
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
244
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
246
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
247
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
249
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
250
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
253
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
254
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
256
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
257
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
259
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
260
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
262
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
263
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
265
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
266
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
268
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
269
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
271
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
272
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
275
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
276
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
278
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
279
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
281
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
282
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
284
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
285
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
287
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
288
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
290
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
291
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
293
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
294
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
297
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
298
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
300
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
301
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
303
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
304
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
306
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
307
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
309
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
310
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
312
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
313
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
315
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
316
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
319
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
320
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
322
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
323
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
325
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
326
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
328
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
329
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
331
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
332
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
334
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
335
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
337
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
338
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
341
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
342
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
344
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
345
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
347
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
348
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
350
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
351
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
353
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
354
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
356
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
357
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
359
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
360
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
363
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
364
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
366
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
367
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
369
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
370
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
372
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
373
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
374
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
375
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
376
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
377
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
378
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
379
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
380
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
381
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
382
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
383
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
384
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
385
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
386
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
387
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
388
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
389
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
390
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
391
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
392
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
393
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
394
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
395
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
396
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
397
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
398
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
399
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
400
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
401
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
402
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
403
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
404
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
405
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
406
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
407
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
408
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
409
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
410
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
411
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
412
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
413
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
414
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
415
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
416
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
417
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
418
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
419
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
420
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
421
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
422
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
423
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
424
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
425
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
426
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
427
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
428
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
429
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
430
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
431
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
432
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
433
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
434
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
435
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
436
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
437
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
438
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
439
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
440
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
441
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
442
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
443
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
444
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
445
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
446
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
447
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
448
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
449
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
450
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
451
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
452
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
453
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
454
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
455
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
456
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
457
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
458
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
459
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
460
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
461
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
462
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
463
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
464
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
465
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
466
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
467
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
468
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
469
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
470
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
471
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
472
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
473
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
474
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
475
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
476
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
477
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
478
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
479
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
480
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
481
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
482
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
483
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
484
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
485
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
486
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
487
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
488
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
489
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
490
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
491
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
492
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
493
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
494
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
495
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
496
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
497
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
498
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
499
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
500
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
501
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
502
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
503
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
504
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
505
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
506
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
507
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
508
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
509
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
510
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
511
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
512
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
513
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
514
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
515
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
516
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
517
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
518
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
519
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
520
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
521
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
522
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
523
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
524
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
525
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
526
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
527
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
528
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
529
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
530
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
531
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
532
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
533
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
534
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
535
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
536
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
537
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
538
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
539
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
540
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
541
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
542
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
543
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
544
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
545
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
546
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
547
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
548
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
549
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
550
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
551
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
552
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
553
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
554
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
555
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
556
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
557
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
558
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
559
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
560
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
561
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
562
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
563
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
564
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
565
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
566
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
567
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
568
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
569
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
570
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
571
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
572
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
573
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
574
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
575
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
576
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
577
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
578
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
579
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
580
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
581
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
582
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
583
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
584
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
585
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
586
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
587
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
588
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
589
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
590
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
591
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
592
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
593
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
594
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
595
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
596
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
597
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
598
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
599
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
600
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
601
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
602
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
603
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
604
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
605
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
606
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
607
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
608
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
609
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
610
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
611
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
612
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
613
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
614
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
615
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
616
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
617
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
618
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
619
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
620
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
621
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
622
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
623
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
624
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
625
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
626
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
627
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
628
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
629
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
630
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
631
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
632
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
633
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
634
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
635
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
636
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
637
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
638
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
639
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
640
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
641
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
642
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
643
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
644
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
645
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
646
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
647
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
648
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
649
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
650
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
651
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
652
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
653
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
654
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
655
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
656
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
657
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
658
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
659
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
660
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
661
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
662
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
663
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
664
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
665
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
666
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
667
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
668
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
669
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
670
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
671
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
672
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
673
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
674
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
675
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
676
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
677
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
678
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
679
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
680
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
681
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
682
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
683
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
684
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
685
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
686
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
687
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
688
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
689
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
690
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
691
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
692
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
693
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
694
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
695
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
696
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
697
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
698
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
699
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
700
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
701
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
702
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
703
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
704
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
705
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
706
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
707
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
708
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
709
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
710
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
711
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
712
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
713
+ "model.norm.weight": "model-00002-of-00002.safetensors"
714
+ }
715
+ }
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:c69a7ea6c0927dfac8c349186ebcf0466a4723c21cbdb2e850cf559f0bee92b8
3
+ size 12777433
tokenizer_config.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% 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
+ "name": "tool_use",
311
+ "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{% for tool in tools %}{% if loop.index0 != 0 %}{{ '\n\n'}}{% endif %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', '}}{% endif %}{{param_name}}: {% if not param_fields.required %}{{'Optional[' + param_fields.type + '] = None'}}{% else %}{{ param_fields.type }}{% endif %}{% endfor %}{{ ') -> List[Dict]:\n \"\"\"'}}{{ tool.description }}{% if tool.parameter_definitions|length != 0 %}{{ '\n\n Args:\n '}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ '\n ' }}{% endif %}{{ param_name + ' ('}}{% if not param_fields.required %}{{'Optional[' + param_fields.type + ']'}}{% else %}{{ param_fields.type }}{% endif %}{{ '): ' + param_fields.description }}{% endfor %}{% endif %}{{ '\n \"\"\"\n pass\n```' }}{% endfor %}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_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 %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n {\n \"tool_name\": title of the tool in the specification,\n \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
312
+ },
313
+ {
314
+ "name": "rag",
315
+ "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_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 %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Carefully perform the following instructions, in order, starting each with a new line.\n' }}{{ 'Firstly, Decide which of the retrieved documents are relevant to the user\\'s last input by writing \\'Relevant Documents:\\' followed by comma-separated list of document numbers. If none are relevant, you should instead write \\'None\\'.\n' }}{{ 'Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user\\'s last input by writing \\'Cited Documents:\\' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write \\'None\\'.\n' }}{% if citation_mode=='accurate' %}{{ 'Thirdly, Write \\'Answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.\n' }}{% endif %}{{ 'Finally, Write \\'Grounded answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
316
+ }
317
+ ],
318
+ "clean_up_tokenization_spaces": false,
319
+ "eos_token": "<|END_OF_TURN_TOKEN|>",
320
+ "legacy": true,
321
+ "merges_file": null,
322
+ "model_max_length": 1000000000000000019884624838656,
323
+ "pad_token": "<PAD>",
324
+ "sp_model_kwargs": {},
325
+ "spaces_between_special_tokens": false,
326
+ "tokenizer_class": "CohereTokenizer",
327
+ "unk_token": null,
328
+ "use_default_system_prompt": false,
329
+ "vocab_file": null
330
+ }