Hugging Face's logo

mlx-community
/
omost-phi-3-mini-128k-mlx-8bit

MLX
Safetensors
PyTorch
phi3
trl
sft
custom_code
Model card Files Community
1

Upload folder using huggingface_hub

#1
by fbjr - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+94297
-0
Files changed (9) hide show
  1. README.md +25 -0
  2. added_tokens.json +13 -0
  3. config.json +140 -0
  4. model.safetensors +3 -0
  5. model.safetensors.index.json +462 -0
  6. special_tokens_map.json +30 -0
  7. tokenizer.json +0 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +130 -0
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - pytorch
4
+ - trl
5
+ - sft
6
+ - mlx
7
+ inference: false
8
+ ---
9
+
10
+ # mlx-community/omost-phi-3-mini-128k-mlx-8bit
11
+
12
+ The Model [mlx-community/omost-phi-3-mini-128k-mlx-8bit](https://huggingface.co/mlx-community/omost-phi-3-mini-128k-mlx-8bit) was converted to MLX format from [lllyasviel/omost-phi-3-mini-128k](https://huggingface.co/lllyasviel/omost-phi-3-mini-128k) using mlx-lm version **0.14.3**.
13
+
14
+ ## Use with mlx
15
+
16
+ ```bash
17
+ pip install mlx-lm
18
+ ```
19
+
20
+ ```python
21
+ from mlx_lm import load, generate
22
+
23
+ model, tokenizer = load("mlx-community/omost-phi-3-mini-128k-mlx-8bit")
24
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
25
+ ```
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "auto_map": {
7
+ "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
8
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
9
+ },
10
+ "bos_token_id": 1,
11
+ "embd_pdrop": 0.0,
12
+ "eos_token_id": 32000,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3072,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 8192,
17
+ "max_position_embeddings": 131072,
18
+ "model_type": "phi3",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 32,
22
+ "original_max_position_embeddings": 4096,
23
+ "pad_token_id": 32000,
24
+ "quantization": {
25
+ "group_size": 128,
26
+ "bits": 8
27
+ },
28
+ "resid_pdrop": 0.0,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_scaling": {
31
+ "long_factor": [
32
+ 1.0299999713897705,
33
+ 1.0499999523162842,
34
+ 1.0499999523162842,
35
+ 1.0799999237060547,
36
+ 1.2299998998641968,
37
+ 1.2299998998641968,
38
+ 1.2999999523162842,
39
+ 1.4499999284744263,
40
+ 1.5999999046325684,
41
+ 1.6499998569488525,
42
+ 1.8999998569488525,
43
+ 2.859999895095825,
44
+ 3.68999981880188,
45
+ 5.419999599456787,
46
+ 5.489999771118164,
47
+ 5.489999771118164,
48
+ 9.09000015258789,
49
+ 11.579999923706055,
50
+ 15.65999984741211,
51
+ 15.769999504089355,
52
+ 15.789999961853027,
53
+ 18.360000610351562,
54
+ 21.989999771118164,
55
+ 23.079999923706055,
56
+ 30.009998321533203,
57
+ 32.35000228881836,
58
+ 32.590003967285156,
59
+ 35.56000518798828,
60
+ 39.95000457763672,
61
+ 53.840003967285156,
62
+ 56.20000457763672,
63
+ 57.95000457763672,
64
+ 59.29000473022461,
65
+ 59.77000427246094,
66
+ 59.920005798339844,
67
+ 61.190006256103516,
68
+ 61.96000671386719,
69
+ 62.50000762939453,
70
+ 63.3700065612793,
71
+ 63.48000717163086,
72
+ 63.48000717163086,
73
+ 63.66000747680664,
74
+ 63.850006103515625,
75
+ 64.08000946044922,
76
+ 64.760009765625,
77
+ 64.80001068115234,
78
+ 64.81001281738281,
79
+ 64.81001281738281
80
+ ],
81
+ "short_factor": [
82
+ 1.05,
83
+ 1.05,
84
+ 1.05,
85
+ 1.1,
86
+ 1.1,
87
+ 1.1500000000000001,
88
+ 1.2000000000000002,
89
+ 1.2500000000000002,
90
+ 1.3000000000000003,
91
+ 1.3500000000000003,
92
+ 1.5000000000000004,
93
+ 2.000000000000001,
94
+ 2.000000000000001,
95
+ 2.000000000000001,
96
+ 2.000000000000001,
97
+ 2.000000000000001,
98
+ 2.000000000000001,
99
+ 2.000000000000001,
100
+ 2.000000000000001,
101
+ 2.000000000000001,
102
+ 2.000000000000001,
103
+ 2.000000000000001,
104
+ 2.000000000000001,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.0500000000000007,
115
+ 2.0500000000000007,
116
+ 2.0500000000000007,
117
+ 2.1000000000000005,
118
+ 2.1000000000000005,
119
+ 2.1000000000000005,
120
+ 2.1500000000000004,
121
+ 2.1500000000000004,
122
+ 2.3499999999999996,
123
+ 2.549999999999999,
124
+ 2.5999999999999988,
125
+ 2.5999999999999988,
126
+ 2.7499999999999982,
127
+ 2.849999999999998,
128
+ 2.849999999999998,
129
+ 2.9499999999999975
130
+ ],
131
+ "type": "su"
132
+ },
133
+ "rope_theta": 10000.0,
134
+ "sliding_window": 262144,
135
+ "tie_word_embeddings": false,
136
+ "torch_dtype": "bfloat16",
137
+ "transformers_version": "4.41.1",
138
+ "use_cache": true,
139
+ "vocab_size": 32064
140
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee2908aaaf2665d279b504bac68a399361b10035ff408c641ac0b445e09494a
3
+ size 3940733775
model.safetensors.index.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 3940681728
4
+ },
5
+ "weight_map": {
6
+ "lm_head.biases": "model.safetensors",
7
+ "lm_head.scales": "model.safetensors",
8
+ "lm_head.weight": "model.safetensors",
9
+ "model.embed_tokens.biases": "model.safetensors",
10
+ "model.embed_tokens.scales": "model.safetensors",
11
+ "model.embed_tokens.weight": "model.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
13
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
14
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
15
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
16
+ "model.layers.0.mlp.gate_up_proj.biases": "model.safetensors",
17
+ "model.layers.0.mlp.gate_up_proj.scales": "model.safetensors",
18
+ "model.layers.0.mlp.gate_up_proj.weight": "model.safetensors",
19
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
20
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
21
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
22
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
23
+ "model.layers.0.self_attn.qkv_proj.biases": "model.safetensors",
24
+ "model.layers.0.self_attn.qkv_proj.scales": "model.safetensors",
25
+ "model.layers.0.self_attn.qkv_proj.weight": "model.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
27
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
28
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
29
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
30
+ "model.layers.1.mlp.gate_up_proj.biases": "model.safetensors",
31
+ "model.layers.1.mlp.gate_up_proj.scales": "model.safetensors",
32
+ "model.layers.1.mlp.gate_up_proj.weight": "model.safetensors",
33
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
34
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
35
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
36
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
37
+ "model.layers.1.self_attn.qkv_proj.biases": "model.safetensors",
38
+ "model.layers.1.self_attn.qkv_proj.scales": "model.safetensors",
39
+ "model.layers.1.self_attn.qkv_proj.weight": "model.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
41
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
42
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
43
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
44
+ "model.layers.10.mlp.gate_up_proj.biases": "model.safetensors",
45
+ "model.layers.10.mlp.gate_up_proj.scales": "model.safetensors",
46
+ "model.layers.10.mlp.gate_up_proj.weight": "model.safetensors",
47
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
48
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
49
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
50
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
51
+ "model.layers.10.self_attn.qkv_proj.biases": "model.safetensors",
52
+ "model.layers.10.self_attn.qkv_proj.scales": "model.safetensors",
53
+ "model.layers.10.self_attn.qkv_proj.weight": "model.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
55
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
56
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
57
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
58
+ "model.layers.11.mlp.gate_up_proj.biases": "model.safetensors",
59
+ "model.layers.11.mlp.gate_up_proj.scales": "model.safetensors",
60
+ "model.layers.11.mlp.gate_up_proj.weight": "model.safetensors",
61
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
62
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
63
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
64
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
65
+ "model.layers.11.self_attn.qkv_proj.biases": "model.safetensors",
66
+ "model.layers.11.self_attn.qkv_proj.scales": "model.safetensors",
67
+ "model.layers.11.self_attn.qkv_proj.weight": "model.safetensors",
68
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
69
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
70
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
71
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
72
+ "model.layers.12.mlp.gate_up_proj.biases": "model.safetensors",
73
+ "model.layers.12.mlp.gate_up_proj.scales": "model.safetensors",
74
+ "model.layers.12.mlp.gate_up_proj.weight": "model.safetensors",
75
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
76
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
77
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
78
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
79
+ "model.layers.12.self_attn.qkv_proj.biases": "model.safetensors",
80
+ "model.layers.12.self_attn.qkv_proj.scales": "model.safetensors",
81
+ "model.layers.12.self_attn.qkv_proj.weight": "model.safetensors",
82
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
83
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
84
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
85
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
86
+ "model.layers.13.mlp.gate_up_proj.biases": "model.safetensors",
87
+ "model.layers.13.mlp.gate_up_proj.scales": "model.safetensors",
88
+ "model.layers.13.mlp.gate_up_proj.weight": "model.safetensors",
89
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
90
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
91
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
92
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
93
+ "model.layers.13.self_attn.qkv_proj.biases": "model.safetensors",
94
+ "model.layers.13.self_attn.qkv_proj.scales": "model.safetensors",
95
+ "model.layers.13.self_attn.qkv_proj.weight": "model.safetensors",
96
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
97
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
98
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
99
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
100
+ "model.layers.14.mlp.gate_up_proj.biases": "model.safetensors",
101
+ "model.layers.14.mlp.gate_up_proj.scales": "model.safetensors",
102
+ "model.layers.14.mlp.gate_up_proj.weight": "model.safetensors",
103
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
104
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
105
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
106
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
107
+ "model.layers.14.self_attn.qkv_proj.biases": "model.safetensors",
108
+ "model.layers.14.self_attn.qkv_proj.scales": "model.safetensors",
109
+ "model.layers.14.self_attn.qkv_proj.weight": "model.safetensors",
110
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
111
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
112
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
113
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
114
+ "model.layers.15.mlp.gate_up_proj.biases": "model.safetensors",
115
+ "model.layers.15.mlp.gate_up_proj.scales": "model.safetensors",
116
+ "model.layers.15.mlp.gate_up_proj.weight": "model.safetensors",
117
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
118
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
119
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
120
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
121
+ "model.layers.15.self_attn.qkv_proj.biases": "model.safetensors",
122
+ "model.layers.15.self_attn.qkv_proj.scales": "model.safetensors",
123
+ "model.layers.15.self_attn.qkv_proj.weight": "model.safetensors",
124
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
125
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
126
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
127
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
128
+ "model.layers.16.mlp.gate_up_proj.biases": "model.safetensors",
129
+ "model.layers.16.mlp.gate_up_proj.scales": "model.safetensors",
130
+ "model.layers.16.mlp.gate_up_proj.weight": "model.safetensors",
131
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
132
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
133
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
134
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
135
+ "model.layers.16.self_attn.qkv_proj.biases": "model.safetensors",
136
+ "model.layers.16.self_attn.qkv_proj.scales": "model.safetensors",
137
+ "model.layers.16.self_attn.qkv_proj.weight": "model.safetensors",
138
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
139
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
140
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
141
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
142
+ "model.layers.17.mlp.gate_up_proj.biases": "model.safetensors",
143
+ "model.layers.17.mlp.gate_up_proj.scales": "model.safetensors",
144
+ "model.layers.17.mlp.gate_up_proj.weight": "model.safetensors",
145
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
146
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
147
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
148
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
149
+ "model.layers.17.self_attn.qkv_proj.biases": "model.safetensors",
150
+ "model.layers.17.self_attn.qkv_proj.scales": "model.safetensors",
151
+ "model.layers.17.self_attn.qkv_proj.weight": "model.safetensors",
152
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
153
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
154
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
155
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
156
+ "model.layers.18.mlp.gate_up_proj.biases": "model.safetensors",
157
+ "model.layers.18.mlp.gate_up_proj.scales": "model.safetensors",
158
+ "model.layers.18.mlp.gate_up_proj.weight": "model.safetensors",
159
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
160
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
161
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
162
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
163
+ "model.layers.18.self_attn.qkv_proj.biases": "model.safetensors",
164
+ "model.layers.18.self_attn.qkv_proj.scales": "model.safetensors",
165
+ "model.layers.18.self_attn.qkv_proj.weight": "model.safetensors",
166
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
167
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
168
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
169
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
170
+ "model.layers.19.mlp.gate_up_proj.biases": "model.safetensors",
171
+ "model.layers.19.mlp.gate_up_proj.scales": "model.safetensors",
172
+ "model.layers.19.mlp.gate_up_proj.weight": "model.safetensors",
173
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
174
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
175
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
176
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
177
+ "model.layers.19.self_attn.qkv_proj.biases": "model.safetensors",
178
+ "model.layers.19.self_attn.qkv_proj.scales": "model.safetensors",
179
+ "model.layers.19.self_attn.qkv_proj.weight": "model.safetensors",
180
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
181
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
182
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
183
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
184
+ "model.layers.2.mlp.gate_up_proj.biases": "model.safetensors",
185
+ "model.layers.2.mlp.gate_up_proj.scales": "model.safetensors",
186
+ "model.layers.2.mlp.gate_up_proj.weight": "model.safetensors",
187
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
188
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
189
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
190
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
191
+ "model.layers.2.self_attn.qkv_proj.biases": "model.safetensors",
192
+ "model.layers.2.self_attn.qkv_proj.scales": "model.safetensors",
193
+ "model.layers.2.self_attn.qkv_proj.weight": "model.safetensors",
194
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
195
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
196
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
197
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
198
+ "model.layers.20.mlp.gate_up_proj.biases": "model.safetensors",
199
+ "model.layers.20.mlp.gate_up_proj.scales": "model.safetensors",
200
+ "model.layers.20.mlp.gate_up_proj.weight": "model.safetensors",
201
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
202
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
203
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
204
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
205
+ "model.layers.20.self_attn.qkv_proj.biases": "model.safetensors",
206
+ "model.layers.20.self_attn.qkv_proj.scales": "model.safetensors",
207
+ "model.layers.20.self_attn.qkv_proj.weight": "model.safetensors",
208
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
209
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
210
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
211
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
212
+ "model.layers.21.mlp.gate_up_proj.biases": "model.safetensors",
213
+ "model.layers.21.mlp.gate_up_proj.scales": "model.safetensors",
214
+ "model.layers.21.mlp.gate_up_proj.weight": "model.safetensors",
215
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
216
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
217
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
218
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
219
+ "model.layers.21.self_attn.qkv_proj.biases": "model.safetensors",
220
+ "model.layers.21.self_attn.qkv_proj.scales": "model.safetensors",
221
+ "model.layers.21.self_attn.qkv_proj.weight": "model.safetensors",
222
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
223
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
224
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
225
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
226
+ "model.layers.22.mlp.gate_up_proj.biases": "model.safetensors",
227
+ "model.layers.22.mlp.gate_up_proj.scales": "model.safetensors",
228
+ "model.layers.22.mlp.gate_up_proj.weight": "model.safetensors",
229
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
230
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
231
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
232
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
233
+ "model.layers.22.self_attn.qkv_proj.biases": "model.safetensors",
234
+ "model.layers.22.self_attn.qkv_proj.scales": "model.safetensors",
235
+ "model.layers.22.self_attn.qkv_proj.weight": "model.safetensors",
236
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
237
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
238
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
239
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
240
+ "model.layers.23.mlp.gate_up_proj.biases": "model.safetensors",
241
+ "model.layers.23.mlp.gate_up_proj.scales": "model.safetensors",
242
+ "model.layers.23.mlp.gate_up_proj.weight": "model.safetensors",
243
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
244
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
245
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
246
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
247
+ "model.layers.23.self_attn.qkv_proj.biases": "model.safetensors",
248
+ "model.layers.23.self_attn.qkv_proj.scales": "model.safetensors",
249
+ "model.layers.23.self_attn.qkv_proj.weight": "model.safetensors",
250
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
251
+ "model.layers.24.mlp.down_proj.biases": "model.safetensors",
252
+ "model.layers.24.mlp.down_proj.scales": "model.safetensors",
253
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
254
+ "model.layers.24.mlp.gate_up_proj.biases": "model.safetensors",
255
+ "model.layers.24.mlp.gate_up_proj.scales": "model.safetensors",
256
+ "model.layers.24.mlp.gate_up_proj.weight": "model.safetensors",
257
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
258
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
259
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
260
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
261
+ "model.layers.24.self_attn.qkv_proj.biases": "model.safetensors",
262
+ "model.layers.24.self_attn.qkv_proj.scales": "model.safetensors",
263
+ "model.layers.24.self_attn.qkv_proj.weight": "model.safetensors",
264
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
265
+ "model.layers.25.mlp.down_proj.biases": "model.safetensors",
266
+ "model.layers.25.mlp.down_proj.scales": "model.safetensors",
267
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
268
+ "model.layers.25.mlp.gate_up_proj.biases": "model.safetensors",
269
+ "model.layers.25.mlp.gate_up_proj.scales": "model.safetensors",
270
+ "model.layers.25.mlp.gate_up_proj.weight": "model.safetensors",
271
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
272
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
273
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
274
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
275
+ "model.layers.25.self_attn.qkv_proj.biases": "model.safetensors",
276
+ "model.layers.25.self_attn.qkv_proj.scales": "model.safetensors",
277
+ "model.layers.25.self_attn.qkv_proj.weight": "model.safetensors",
278
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
279
+ "model.layers.26.mlp.down_proj.biases": "model.safetensors",
280
+ "model.layers.26.mlp.down_proj.scales": "model.safetensors",
281
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
282
+ "model.layers.26.mlp.gate_up_proj.biases": "model.safetensors",
283
+ "model.layers.26.mlp.gate_up_proj.scales": "model.safetensors",
284
+ "model.layers.26.mlp.gate_up_proj.weight": "model.safetensors",
285
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
286
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
287
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
288
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
289
+ "model.layers.26.self_attn.qkv_proj.biases": "model.safetensors",
290
+ "model.layers.26.self_attn.qkv_proj.scales": "model.safetensors",
291
+ "model.layers.26.self_attn.qkv_proj.weight": "model.safetensors",
292
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
293
+ "model.layers.27.mlp.down_proj.biases": "model.safetensors",
294
+ "model.layers.27.mlp.down_proj.scales": "model.safetensors",
295
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
296
+ "model.layers.27.mlp.gate_up_proj.biases": "model.safetensors",
297
+ "model.layers.27.mlp.gate_up_proj.scales": "model.safetensors",
298
+ "model.layers.27.mlp.gate_up_proj.weight": "model.safetensors",
299
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
300
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
301
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
302
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
303
+ "model.layers.27.self_attn.qkv_proj.biases": "model.safetensors",
304
+ "model.layers.27.self_attn.qkv_proj.scales": "model.safetensors",
305
+ "model.layers.27.self_attn.qkv_proj.weight": "model.safetensors",
306
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
307
+ "model.layers.28.mlp.down_proj.biases": "model.safetensors",
308
+ "model.layers.28.mlp.down_proj.scales": "model.safetensors",
309
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
310
+ "model.layers.28.mlp.gate_up_proj.biases": "model.safetensors",
311
+ "model.layers.28.mlp.gate_up_proj.scales": "model.safetensors",
312
+ "model.layers.28.mlp.gate_up_proj.weight": "model.safetensors",
313
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
314
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
315
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
316
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
317
+ "model.layers.28.self_attn.qkv_proj.biases": "model.safetensors",
318
+ "model.layers.28.self_attn.qkv_proj.scales": "model.safetensors",
319
+ "model.layers.28.self_attn.qkv_proj.weight": "model.safetensors",
320
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
321
+ "model.layers.29.mlp.down_proj.biases": "model.safetensors",
322
+ "model.layers.29.mlp.down_proj.scales": "model.safetensors",
323
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
324
+ "model.layers.29.mlp.gate_up_proj.biases": "model.safetensors",
325
+ "model.layers.29.mlp.gate_up_proj.scales": "model.safetensors",
326
+ "model.layers.29.mlp.gate_up_proj.weight": "model.safetensors",
327
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
328
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
329
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
330
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
331
+ "model.layers.29.self_attn.qkv_proj.biases": "model.safetensors",
332
+ "model.layers.29.self_attn.qkv_proj.scales": "model.safetensors",
333
+ "model.layers.29.self_attn.qkv_proj.weight": "model.safetensors",
334
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
335
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
336
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
337
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
338
+ "model.layers.3.mlp.gate_up_proj.biases": "model.safetensors",
339
+ "model.layers.3.mlp.gate_up_proj.scales": "model.safetensors",
340
+ "model.layers.3.mlp.gate_up_proj.weight": "model.safetensors",
341
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
342
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
343
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
344
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
345
+ "model.layers.3.self_attn.qkv_proj.biases": "model.safetensors",
346
+ "model.layers.3.self_attn.qkv_proj.scales": "model.safetensors",
347
+ "model.layers.3.self_attn.qkv_proj.weight": "model.safetensors",
348
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
349
+ "model.layers.30.mlp.down_proj.biases": "model.safetensors",
350
+ "model.layers.30.mlp.down_proj.scales": "model.safetensors",
351
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
352
+ "model.layers.30.mlp.gate_up_proj.biases": "model.safetensors",
353
+ "model.layers.30.mlp.gate_up_proj.scales": "model.safetensors",
354
+ "model.layers.30.mlp.gate_up_proj.weight": "model.safetensors",
355
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
356
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
357
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
358
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
359
+ "model.layers.30.self_attn.qkv_proj.biases": "model.safetensors",
360
+ "model.layers.30.self_attn.qkv_proj.scales": "model.safetensors",
361
+ "model.layers.30.self_attn.qkv_proj.weight": "model.safetensors",
362
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
363
+ "model.layers.31.mlp.down_proj.biases": "model.safetensors",
364
+ "model.layers.31.mlp.down_proj.scales": "model.safetensors",
365
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
366
+ "model.layers.31.mlp.gate_up_proj.biases": "model.safetensors",
367
+ "model.layers.31.mlp.gate_up_proj.scales": "model.safetensors",
368
+ "model.layers.31.mlp.gate_up_proj.weight": "model.safetensors",
369
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
370
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
371
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
372
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
373
+ "model.layers.31.self_attn.qkv_proj.biases": "model.safetensors",
374
+ "model.layers.31.self_attn.qkv_proj.scales": "model.safetensors",
375
+ "model.layers.31.self_attn.qkv_proj.weight": "model.safetensors",
376
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
377
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
378
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
379
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
380
+ "model.layers.4.mlp.gate_up_proj.biases": "model.safetensors",
381
+ "model.layers.4.mlp.gate_up_proj.scales": "model.safetensors",
382
+ "model.layers.4.mlp.gate_up_proj.weight": "model.safetensors",
383
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
384
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
385
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
386
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
387
+ "model.layers.4.self_attn.qkv_proj.biases": "model.safetensors",
388
+ "model.layers.4.self_attn.qkv_proj.scales": "model.safetensors",
389
+ "model.layers.4.self_attn.qkv_proj.weight": "model.safetensors",
390
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
391
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
392
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
393
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
394
+ "model.layers.5.mlp.gate_up_proj.biases": "model.safetensors",
395
+ "model.layers.5.mlp.gate_up_proj.scales": "model.safetensors",
396
+ "model.layers.5.mlp.gate_up_proj.weight": "model.safetensors",
397
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
398
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
399
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
400
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
401
+ "model.layers.5.self_attn.qkv_proj.biases": "model.safetensors",
402
+ "model.layers.5.self_attn.qkv_proj.scales": "model.safetensors",
403
+ "model.layers.5.self_attn.qkv_proj.weight": "model.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
405
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
406
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
407
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
408
+ "model.layers.6.mlp.gate_up_proj.biases": "model.safetensors",
409
+ "model.layers.6.mlp.gate_up_proj.scales": "model.safetensors",
410
+ "model.layers.6.mlp.gate_up_proj.weight": "model.safetensors",
411
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
412
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
413
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
414
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
415
+ "model.layers.6.self_attn.qkv_proj.biases": "model.safetensors",
416
+ "model.layers.6.self_attn.qkv_proj.scales": "model.safetensors",
417
+ "model.layers.6.self_attn.qkv_proj.weight": "model.safetensors",
418
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
419
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
420
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
421
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
422
+ "model.layers.7.mlp.gate_up_proj.biases": "model.safetensors",
423
+ "model.layers.7.mlp.gate_up_proj.scales": "model.safetensors",
424
+ "model.layers.7.mlp.gate_up_proj.weight": "model.safetensors",
425
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
426
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
427
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
428
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
429
+ "model.layers.7.self_attn.qkv_proj.biases": "model.safetensors",
430
+ "model.layers.7.self_attn.qkv_proj.scales": "model.safetensors",
431
+ "model.layers.7.self_attn.qkv_proj.weight": "model.safetensors",
432
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
433
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
434
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
435
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
436
+ "model.layers.8.mlp.gate_up_proj.biases": "model.safetensors",
437
+ "model.layers.8.mlp.gate_up_proj.scales": "model.safetensors",
438
+ "model.layers.8.mlp.gate_up_proj.weight": "model.safetensors",
439
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
440
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
441
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
442
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
443
+ "model.layers.8.self_attn.qkv_proj.biases": "model.safetensors",
444
+ "model.layers.8.self_attn.qkv_proj.scales": "model.safetensors",
445
+ "model.layers.8.self_attn.qkv_proj.weight": "model.safetensors",
446
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
447
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
448
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
449
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
450
+ "model.layers.9.mlp.gate_up_proj.biases": "model.safetensors",
451
+ "model.layers.9.mlp.gate_up_proj.scales": "model.safetensors",
452
+ "model.layers.9.mlp.gate_up_proj.weight": "model.safetensors",
453
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
454
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
455
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
456
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
457
+ "model.layers.9.self_attn.qkv_proj.biases": "model.safetensors",
458
+ "model.layers.9.self_attn.qkv_proj.scales": "model.safetensors",
459
+ "model.layers.9.self_attn.qkv_proj.weight": "model.safetensors",
460
+ "model.norm.weight": "model.safetensors"
461
+ }
462
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ }
117
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 131072,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
130
+ }