intervitens
commited on
Commit
•
7d91e7a
1
Parent(s):
d5b90b8
Upload folder using huggingface_hub
Browse files- README.md +48 -0
- config.json +30 -0
- mergekit_config.yml +15 -0
- output-00001-of-00005.safetensors +3 -0
- output-00002-of-00005.safetensors +3 -0
- output-00003-of-00005.safetensors +3 -0
- output-00004-of-00005.safetensors +3 -0
- output-00005-of-00005.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
tags:
|
4 |
+
- mergekit
|
5 |
+
- merge
|
6 |
+
|
7 |
+
---
|
8 |
+
# Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES
|
9 |
+
|
10 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
11 |
+
|
12 |
+
## Merge Details
|
13 |
+
|
14 |
+
An experimental merge.
|
15 |
+
|
16 |
+
Prompt format: ChatML or Mixtral-8x7B-Instruct-v0.1
|
17 |
+
|
18 |
+
### Merge Method
|
19 |
+
|
20 |
+
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using ./models/Mixtral-8x7B-v0.1 as a base.
|
21 |
+
|
22 |
+
### Models Merged
|
23 |
+
|
24 |
+
The following models were included in the merge:
|
25 |
+
* [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
|
26 |
+
* [Nous-Hermes-2-Mixtral-8x7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)
|
27 |
+
|
28 |
+
### Configuration
|
29 |
+
|
30 |
+
The following YAML configuration was used to produce this model:
|
31 |
+
|
32 |
+
```yaml
|
33 |
+
models:
|
34 |
+
- model: ./models/Mixtral-8x7B-Instruct-v0.1
|
35 |
+
parameters:
|
36 |
+
density: 0.5
|
37 |
+
weight: 1.0
|
38 |
+
- model: ./models/Nous-Hermes-2-Mixtral-8x7B-DPO
|
39 |
+
parameters:
|
40 |
+
density: 0.5
|
41 |
+
weight: 0.5
|
42 |
+
merge_method: dare_ties
|
43 |
+
base_model: ./models/Mixtral-8x7B-v0.1
|
44 |
+
parameters:
|
45 |
+
#normalize: false
|
46 |
+
#int8_mask: true
|
47 |
+
dtype: bfloat16
|
48 |
+
```
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./models/Mixtral-8x7B-v0.1",
|
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": 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": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"router_aux_loss_coef": 0.02,
|
24 |
+
"sliding_window": null,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.36.2",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: ./models/Mixtral-8x7B-Instruct-v0.1
|
3 |
+
parameters:
|
4 |
+
density: 0.5
|
5 |
+
weight: 1.0
|
6 |
+
- model: ./models/Nous-Hermes-2-Mixtral-8x7B-DPO
|
7 |
+
parameters:
|
8 |
+
density: 0.5
|
9 |
+
weight: 0.5
|
10 |
+
merge_method: dare_ties
|
11 |
+
base_model: ./models/Mixtral-8x7B-v0.1
|
12 |
+
parameters:
|
13 |
+
#normalize: false
|
14 |
+
#int8_mask: true
|
15 |
+
dtype: bfloat16
|
output-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c6dd4aa24950f50351fd36eaca5d2197f4e4801f266309fc014ac2d6c744e0e
|
3 |
+
size 8588808872
|
output-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c29e4d1258474ca0a9c62edd4e6da8e82857bb5112b93dfbd1f7ddff0a5b90c9
|
3 |
+
size 8573867144
|
output-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1b7c48475d09aa7f7eed848590298dd7c902c70d2b70dc59361a80aec81c6e6
|
3 |
+
size 8554397512
|
output-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22cff1b3027acfeff868eda324201c392588f8c0265701128cb26dcab956295a
|
3 |
+
size 8589941768
|
output-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9fe4b6f593bbb52ff30de1db56487cba572cc1cfe7c9d6c26687dd632618257
|
3 |
+
size 916816752
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|