Upload model weights (#1)
Browse files- 6e216a9de97d10086d3955aedeea21cf753c7b3a6a8a4ca2e68a458df7257172 (aa4faff33c3d49951138646b12e0a9c1bbab0df7)
- a764a25f6a733bac4f4ddf17a3624dedeb71b913766ce04c19918e0fa4cb2ce8 (f999b8681fc44aacb244214d478f7bd3e4dbeb47)
- 10266a03e975e83492a63cc6454454c3c2f67e44b821e10216f52eea64c968d5 (afb5791ce05e89e8ad19a9ca176889b9f08ba347)
- af2b400764717725fb40f636ef3bb53cd2061fb4f9b485cc6ea7b6dae8c55c07 (4ba91fd99ca221a38614a88a7ca8518a4507df5e)
- e6a970f1279a5604fecd410b48d28187d50f25c9a9f4da2ce284cf14d04e465f (cd36ee43c4981fd7bc8afc3b1f2f350c1ebf76de)
- d7c1c6d4c7253fbd9ce283f9fb92331ac374dfff7370c527920634024ffd1ded (bed2b31a1de55ec13195b942c759fe965217d5fd)
- 4db53726bc59bbd14b94a399e86063dbf0c053eae88df122afd3d0e153a049c2 (0fbbd3f94193e6f0457cf68ef303a65509912a54)
- 73cc2fac3231b61d020aa71132a525c704cea6246162c403e2d487e7db7b7bfa (8c18f5d06cbadde212e1c63e81726ff11a57ba4f)
- 35199060f04dd4fc381393e22ee1e28aea030dc55d918eee997859503bb8aa80 (3ab8ef12c828b0d0abd02cb003193a491a9c0c64)
- README.md +49 -0
- config.json +42 -0
- mergekit_config.yml +10 -0
- model.safetensors.index.json +0 -0
- output-00001-of-00009.safetensors +3 -0
- output-00002-of-00009.safetensors +3 -0
- output-00003-of-00009.safetensors +3 -0
- output-00004-of-00009.safetensors +3 -0
- output-00005-of-00009.safetensors +3 -0
- output-00006-of-00009.safetensors +3 -0
- output-00007-of-00009.safetensors +3 -0
- output-00008-of-00009.safetensors +3 -0
- output-00009-of-00009.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- alpindale/WizardLM-2-8x22B
|
4 |
+
- lightblue/Karasu-Mixtral-8x22B-v0.1
|
5 |
+
- openbmb/Eurux-8x22b-nca
|
6 |
+
- cognitivecomputations/dolphin-2.9.2-mixtral-8x22b
|
7 |
+
- migtissera/Tess-2.0-Mixtral-8x22B
|
8 |
+
- fireworks-ai/mixtral-8x22b-instruct-oh
|
9 |
+
library_name: transformers
|
10 |
+
tags:
|
11 |
+
- mergekit
|
12 |
+
- merge
|
13 |
+
|
14 |
+
---
|
15 |
+
# Untitled Model (1)
|
16 |
+
|
17 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
18 |
+
|
19 |
+
## Merge Details
|
20 |
+
### Merge Method
|
21 |
+
|
22 |
+
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [alpindale/WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B) as a base.
|
23 |
+
|
24 |
+
### Models Merged
|
25 |
+
|
26 |
+
The following models were included in the merge:
|
27 |
+
* [lightblue/Karasu-Mixtral-8x22B-v0.1](https://huggingface.co/lightblue/Karasu-Mixtral-8x22B-v0.1)
|
28 |
+
* [openbmb/Eurux-8x22b-nca](https://huggingface.co/openbmb/Eurux-8x22b-nca)
|
29 |
+
* [cognitivecomputations/dolphin-2.9.2-mixtral-8x22b](https://huggingface.co/cognitivecomputations/dolphin-2.9.2-mixtral-8x22b)
|
30 |
+
* [migtissera/Tess-2.0-Mixtral-8x22B](https://huggingface.co/migtissera/Tess-2.0-Mixtral-8x22B)
|
31 |
+
* [fireworks-ai/mixtral-8x22b-instruct-oh](https://huggingface.co/fireworks-ai/mixtral-8x22b-instruct-oh)
|
32 |
+
|
33 |
+
### Configuration
|
34 |
+
|
35 |
+
The following YAML configuration was used to produce this model:
|
36 |
+
|
37 |
+
```yaml
|
38 |
+
models:
|
39 |
+
- model: alpindale/WizardLM-2-8x22B
|
40 |
+
- model: lightblue/Karasu-Mixtral-8x22B-v0.1
|
41 |
+
- model: fireworks-ai/mixtral-8x22b-instruct-oh
|
42 |
+
- model: cognitivecomputations/dolphin-2.9.2-mixtral-8x22b
|
43 |
+
- model: openbmb/Eurux-8x22b-nca
|
44 |
+
- model: migtissera/Tess-2.0-Mixtral-8x22B
|
45 |
+
base_model: alpindale/WizardLM-2-8x22B
|
46 |
+
merge_method: model_stock
|
47 |
+
dtype: bfloat16
|
48 |
+
|
49 |
+
```
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "alpindale/WizardLM-2-8x22B",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.41.2",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 32000,
|
31 |
+
"quantization_config": {
|
32 |
+
"quant_method": "exl2",
|
33 |
+
"version": "0.1.5",
|
34 |
+
"bits": 4.0,
|
35 |
+
"head_bits": 8,
|
36 |
+
"calibration": {
|
37 |
+
"rows": 100,
|
38 |
+
"length": 2048,
|
39 |
+
"dataset": "(default)"
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: alpindale/WizardLM-2-8x22B
|
3 |
+
- model: lightblue/Karasu-Mixtral-8x22B-v0.1
|
4 |
+
- model: fireworks-ai/mixtral-8x22b-instruct-oh
|
5 |
+
- model: cognitivecomputations/dolphin-2.9.2-mixtral-8x22b
|
6 |
+
- model: openbmb/Eurux-8x22b-nca
|
7 |
+
- model: migtissera/Tess-2.0-Mixtral-8x22B
|
8 |
+
base_model: alpindale/WizardLM-2-8x22B
|
9 |
+
merge_method: model_stock
|
10 |
+
dtype: bfloat16
|
The diff for this file is too large to render.
See raw diff
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a591eab53bbc2c0e5e148e9519c76c686f6ae9fb9768860ff8b4ce08f3428523
|
3 |
+
size 8580907600
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd29d89e7316adb8c594c25019ddfacdf21d11b809b6a2aa9578c3a434bff435
|
3 |
+
size 8544364032
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847255f59dbe3563c9bf75eefd709174494d1084ad18fc6117bda6edb0926a66
|
3 |
+
size 8589756280
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db87c2151175e5331649a8886a44635f82dad81a303ab08c71111f75120aa231
|
3 |
+
size 8586933800
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bc9e349a4f8d5f23fe42a24f217962b635e5836af2f7ca40dda4102f09059d1
|
3 |
+
size 8558700576
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45c861075dfaf00fe8dff97a601ffc4ec8f0230ce3fc52f49cac397dac98e54d
|
3 |
+
size 8589525528
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4101f1fcd2d3bc5d0b45b2fcdabb3fcee1a4443de0c53048577354fef56f6321
|
3 |
+
size 8555766200
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:705c6849a2d76a9a07c7da7969a7cb27285d0f3ad515629ca743057829f52fe7
|
3 |
+
size 8589628776
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7090506d4a9a57b2798dcdf971ead61d0ffc672fa0f9eab52d1cc98ea6b75603
|
3 |
+
size 2033915552
|
@@ -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": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
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 |
+
}
|
The diff for this file is too large to render.
See raw diff
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{{ messages[0]['content'].strip() }}{% else %}{% set loop_messages = messages %}{{ 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions.' }}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ ' USER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% else %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ '\nUSER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ASSISTANT:' }}{% endif %}",
|
34 |
+
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "</s>",
|
36 |
+
"legacy": true,
|
37 |
+
"model_max_length": 1000000000000000019884624838656,
|
38 |
+
"pad_token": "<unk>",
|
39 |
+
"padding_side": "right",
|
40 |
+
"sp_model_kwargs": {},
|
41 |
+
"spaces_between_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": true
|
45 |
+
}
|