redmoe-ai-v1 commited on
Commit
a4ba32a
·
verified ·
1 Parent(s): 6f996ab

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +0,0 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Dotsl1ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "eos_token_id": 151643,
9
+ "first_k_dense_replace": 1,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 10944,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "dots1",
16
+ "moe_intermediate_size": 1408,
17
+ "moe_layer_freq": 1,
18
+ "n_routed_experts": 64,
19
+ "n_shared_experts": 2,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 16,
22
+ "num_experts_per_tok": 6,
23
+ "num_hidden_layers": 27,
24
+ "num_key_value_heads": 16,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000,
29
+ "routed_scaling_factor": 1.0,
30
+ "sliding_window": null,
31
+ "scoring_func": "noaux_tc",
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.3",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 152064
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": null,
4
+ "eos_token_id": 151643,
5
+ "transformers_version": "4.46.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa23daea19cb51c3bc3b8c07ae5929b30de66a9347aa61c3bcd7eabeab1c826a
3
+ size 4290081208
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989a00eb06e66f33a42490f47c294f7013d9151045448a5aba033372545e2d07
3
+ size 4293523288
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02becbc0b3aa81f7592a71dba3ef70ca0880ba9c53b3289ba023a3f57849baa6
3
+ size 4294300744
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38e3b798ac7d66a3fe76d7b8a89f14547c5b739fa07ca0e81c0901c7fcf75fd5
3
+ size 4293523088
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3af1628c7fc91db57cdf9ad69814284c49778f3605958af65f0b473d50618b
3
+ size 4293523288
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9519cfd4b9120c9a4015fe1944a2dc34d7620122d06cb6bdeaf3f2701f886d
3
+ size 4294300392
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bc1866c21fe39a7b79dd96db76876a3dba8ff62fbde9e3bc325abe788aa226
3
+ size 4293522544
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8037f8fb014952226f5305b91e70057eedb8936a60c71267bca74e8c59a1aa55
3
+ size 1930487624
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|userprompt|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|endofuserprompt|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|response|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|endofresponse|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|system|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|endofsystem|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|observation|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|endofobservation|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|execution|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|endofexecution|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|reject-unknown|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<|sec-cot|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "151658": {
125
+ "content": "<|sec-end-cot|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ }
132
+ },
133
+ "additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<|userprompt|>", "<|endofuserprompt|>", "<|response|>", "<|endofresponse|>", "<|system|>", "<|endofsystem|>", "<|observation|>", "<|endofobservation|>", "<|execution|>", "<|endofexecution|>", "<|reject-unknown|>", "<|sec-cot|>", "<|sec-end-cot|>"],
134
+ "bos_token": null,
135
+ "chat_template": "{% if messages[0]['role'] == 'system' %}<|system|>{{ messages[0]['content'] }}<|endofsystem|>{% set start_idx = 1 %}{% else %}<|system|><|endofsystem|>{% set start_idx = 0 %}{% endif %}{% for idx in range(start_idx, messages|length) %}{% if messages[idx]['role'] == 'user' %}<|userprompt|>{{ messages[idx]['content'] }}<|endofuserprompt|>{% elif messages[idx]['role'] == 'assistant' %}<|response|>{{ messages[idx]['content'] }}<|endofresponse|>{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] == 'user' %}<|response|>{% endif %}",
136
+ "clean_up_tokenization_spaces": false,
137
+ "eos_token": "<|endoftext|>",
138
+ "errors": "replace",
139
+ "model_max_length": 32768,
140
+ "pad_token": "<|endoftext|>",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }