Upload folder using huggingface_hub
Browse files- added_tokens.json +4 -0
- config.json +30 -0
- mergekit_moe_config.yml +114 -0
- model-00001-of-00018.safetensors +3 -0
- model-00002-of-00018.safetensors +3 -0
- model-00003-of-00018.safetensors +3 -0
- model-00004-of-00018.safetensors +3 -0
- model-00005-of-00018.safetensors +3 -0
- model-00006-of-00018.safetensors +3 -0
- model-00007-of-00018.safetensors +3 -0
- model-00008-of-00018.safetensors +3 -0
- model-00009-of-00018.safetensors +3 -0
- model-00010-of-00018.safetensors +3 -0
- model-00011-of-00018.safetensors +3 -0
- model-00012-of-00018.safetensors +3 -0
- model-00013-of-00018.safetensors +3 -0
- model-00014-of-00018.safetensors +3 -0
- model-00015-of-00018.safetensors +3 -0
- model-00016-of-00018.safetensors +3 -0
- model-00017-of-00018.safetensors +3 -0
- model-00018-of-00018.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +61 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openaccess-ai-collective/DPOpenHermes-7B",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 15,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"sliding_window": null,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.37.2",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 32002
|
30 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: openaccess-ai-collective/DPOpenHermes-7B
|
2 |
+
dtype: bfloat16
|
3 |
+
experts:
|
4 |
+
- positive_prompts:
|
5 |
+
- instruction
|
6 |
+
- solutions
|
7 |
+
- chat
|
8 |
+
- questions
|
9 |
+
- comprehension
|
10 |
+
source_model: teknium/OpenHermes-2.5-Mistral-7B
|
11 |
+
- negative_prompts:
|
12 |
+
- chat
|
13 |
+
- questions
|
14 |
+
- python
|
15 |
+
positive_prompts:
|
16 |
+
- coding
|
17 |
+
- programming
|
18 |
+
- code
|
19 |
+
- programming language
|
20 |
+
source_model: codellama/CodeLlama-13b-hf
|
21 |
+
- negative_prompts:
|
22 |
+
- chat
|
23 |
+
- questions
|
24 |
+
positive_prompts:
|
25 |
+
- python
|
26 |
+
- pip
|
27 |
+
- coding
|
28 |
+
- programming
|
29 |
+
- code
|
30 |
+
- programming language
|
31 |
+
source_model: codellama/CodeLlama-13b-Python-hf
|
32 |
+
- negative_prompts:
|
33 |
+
- chat
|
34 |
+
- questions
|
35 |
+
positive_prompts:
|
36 |
+
- mathematics
|
37 |
+
- optimization
|
38 |
+
- step-by-step
|
39 |
+
- science
|
40 |
+
source_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo
|
41 |
+
- negative_prompts:
|
42 |
+
- chat
|
43 |
+
- questions
|
44 |
+
positive_prompts:
|
45 |
+
- bedtime story
|
46 |
+
- Once upon a time
|
47 |
+
- storytelling
|
48 |
+
- narrator
|
49 |
+
source_model: tom92119/llama-2-7b-bedtime-story
|
50 |
+
- negative_prompts:
|
51 |
+
- chat
|
52 |
+
- questions
|
53 |
+
positive_prompts:
|
54 |
+
- story
|
55 |
+
- Once upon a time
|
56 |
+
- storytelling
|
57 |
+
- narrator
|
58 |
+
source_model: Norquinal/Mistral-7B-storywriter
|
59 |
+
- negative_prompts:
|
60 |
+
- chat
|
61 |
+
- questions
|
62 |
+
- instruction
|
63 |
+
- solutions
|
64 |
+
- chat
|
65 |
+
- comprehension
|
66 |
+
- mathematics
|
67 |
+
- optimization
|
68 |
+
- code
|
69 |
+
- step-by-step
|
70 |
+
- science
|
71 |
+
positive_prompts:
|
72 |
+
- function calls
|
73 |
+
- functions
|
74 |
+
- constrained grammar
|
75 |
+
- API calls
|
76 |
+
- LLM Tools
|
77 |
+
source_model: meetkai/functionary-small-v2.2
|
78 |
+
- positive_prompts:
|
79 |
+
- indonesian
|
80 |
+
- indonesia
|
81 |
+
source_model: azale-ai/Starstreak-7b-beta
|
82 |
+
- positive_prompts:
|
83 |
+
- arabic
|
84 |
+
- arab
|
85 |
+
source_model: gagan3012/Mistral_arabic_dpo
|
86 |
+
- positive_prompts:
|
87 |
+
- korean
|
88 |
+
- korea
|
89 |
+
source_model: davidkim205/komt-mistral-7b-v1
|
90 |
+
- positive_prompts:
|
91 |
+
- chinese
|
92 |
+
- china
|
93 |
+
source_model: OpenBuddy/openbuddy-zephyr-7b-v14.1
|
94 |
+
- positive_prompts:
|
95 |
+
- hindi
|
96 |
+
- india
|
97 |
+
source_model: manishiitg/open-aditi-hi-v1
|
98 |
+
- positive_prompts:
|
99 |
+
- german
|
100 |
+
- deutsch
|
101 |
+
- Germany
|
102 |
+
source_model: VAGOsolutions/SauerkrautLM-7b-v1-mistral
|
103 |
+
- positive_prompts:
|
104 |
+
- Norway
|
105 |
+
- Norwegian
|
106 |
+
- Norsk
|
107 |
+
source_model: bineric/NorskGPT-Mistral-7b
|
108 |
+
- positive_prompts:
|
109 |
+
- Russian
|
110 |
+
- Russia
|
111 |
+
- "\u0420\u0443\u0441\u0441\u043A\u0438\u0439"
|
112 |
+
- "\u0420\u043E\u0441\u0441\u0438\u044F"
|
113 |
+
source_model: Droidfanat/llama-2-7b-custom-russian
|
114 |
+
gate_mode: hidden
|
model-00001-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9475db8ee8eeaf4d363e465dfa73198cfb54aaa0a0519122d1fb5e6c447ef143
|
3 |
+
size 9909360696
|
model-00002-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b74d21b04319c876416bee1305cd65fa4e297f8aaa3674dbd00313d1e7eccc14
|
3 |
+
size 9923734464
|
model-00003-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:987917a6a3b7d8d9056372c3af6eb28df143477edf027d849bbad8750951f24f
|
3 |
+
size 9971969024
|
model-00004-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31ac788de56184d9e7ea80dbdf34199eada2a8215f738f682e391538dd3a6781
|
3 |
+
size 9944706056
|
model-00005-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18a98c42d1198fafaa07881cba507b05107a0b2aadc0e827cad4b580b74dbff3
|
3 |
+
size 9923734536
|
model-00006-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1346c1985234956bbff1583641744998ff18d4dbf27336fb1011dbefa01a748d
|
3 |
+
size 9971969000
|
model-00007-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d424a089be9c4028cc76648321876ae32a5348ce8f35270cd6d765e53a1eb97d
|
3 |
+
size 9944705968
|
model-00008-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07a8e5a05c1b9115634422df975d2d85a462865d8dbb6a728f97bdb1a9ca1dbf
|
3 |
+
size 9923734496
|
model-00009-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ee619ca21146109d1929027fd10a4c8a81c29ed2bca711f1531066568d7ace6
|
3 |
+
size 9971969024
|
model-00010-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a1afb8049fbb6b08071bf72631c7abc68af97d59168aa6344fe3d17baf3c8f8
|
3 |
+
size 9944706056
|
model-00011-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5c50da8d197fe4afdc75f07f42a54df0a8cda173ed8b0d364ee7854da3aef6b
|
3 |
+
size 9923734536
|
model-00012-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c99ca953a8f04cd7342273d56c35e05ca5e2d31ba0ea537324da7a76f8cb80d
|
3 |
+
size 9971968968
|
model-00013-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81cc301852e9846b52a2bec9f1d78817da51fdc9830c3987a0f5849247755814
|
3 |
+
size 9944705968
|
model-00014-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f07993c466d3eea4e1e5a3c2f2dcda41abdf0de4cdcca7547502d8399e2dc406
|
3 |
+
size 9923734520
|
model-00015-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe9b3fdeb0360990620ac981e4817929cf9c082bd131f374040af7ed7fdd7cfb
|
3 |
+
size 9971969024
|
model-00016-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc2824a7753e19f06cac646f3a541da3e44f4cc2a4017208500e1c70bbe0331a
|
3 |
+
size 9944706056
|
model-00017-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f15efdc4791f187e5407a165be31912a5af52e4e8b6e24e52893d944d78c5439
|
3 |
+
size 9991109544
|
model-00018-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33fc89bca82a1caec48825f88951c3e4a236b450a21deb17a9879f39a65f8aea
|
3 |
+
size 2621196440
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|im_end|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|im_start|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"additional_special_tokens": [],
|
47 |
+
"bos_token": "<s>",
|
48 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
49 |
+
"clean_up_tokenization_spaces": false,
|
50 |
+
"eos_token": "<|im_end|>",
|
51 |
+
"legacy": true,
|
52 |
+
"model_max_length": 1000000000000000019884624838656,
|
53 |
+
"pad_token": "<s>",
|
54 |
+
"sp_model_kwargs": {},
|
55 |
+
"spaces_between_special_tokens": false,
|
56 |
+
"tokenizer_class": "LlamaTokenizer",
|
57 |
+
"trust_remote_code": false,
|
58 |
+
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": true,
|
60 |
+
"use_fast": true
|
61 |
+
}
|