ClaudioItaly commited on
Commit
3eefb92
1 Parent(s): 4e8520d

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,7 +1,8 @@
1
  ---
2
  base_model:
3
- - Nitral-AI/Prima-LelantaclesV6-7b
4
  - mergekit-community/TopEvolution
 
 
5
  library_name: transformers
6
  tags:
7
  - mergekit
@@ -15,13 +16,13 @@ This is a merge of pre-trained language models created using [mergekit](https://
15
  ## Merge Details
16
  ### Merge Method
17
 
18
- This model was merged using the SLERP merge method.
19
 
20
  ### Models Merged
21
 
22
  The following models were included in the merge:
23
- * [Nitral-AI/Prima-LelantaclesV6-7b](https://huggingface.co/Nitral-AI/Prima-LelantaclesV6-7b)
24
- * [mergekit-community/TopEvolution](https://huggingface.co/mergekit-community/TopEvolution)
25
 
26
  ### Configuration
27
 
@@ -29,12 +30,19 @@ The following YAML configuration was used to produce this model:
29
 
30
  ```yaml
31
  models:
32
- - model: Nitral-AI/Prima-LelantaclesV6-7b
33
- - model: mergekit-community/TopEvolution
34
- merge_method: slerp
 
 
 
 
 
 
 
35
  base_model: mergekit-community/TopEvolution
36
- dtype: bfloat16
37
  parameters:
38
- t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
39
-
 
40
  ```
 
1
  ---
2
  base_model:
 
3
  - mergekit-community/TopEvolution
4
+ - ClaudioItaly/Evolutionstory
5
+ - lucyknada/microsoft_WizardLM-2-7B
6
  library_name: transformers
7
  tags:
8
  - mergekit
 
16
  ## Merge Details
17
  ### Merge Method
18
 
19
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [mergekit-community/TopEvolution](https://huggingface.co/mergekit-community/TopEvolution) as a base.
20
 
21
  ### Models Merged
22
 
23
  The following models were included in the merge:
24
+ * [ClaudioItaly/Evolutionstory](https://huggingface.co/ClaudioItaly/Evolutionstory)
25
+ * [lucyknada/microsoft_WizardLM-2-7B](https://huggingface.co/lucyknada/microsoft_WizardLM-2-7B)
26
 
27
  ### Configuration
28
 
 
30
 
31
  ```yaml
32
  models:
33
+ - model: ClaudioItaly/Evolutionstory
34
+ parameters:
35
+ density: 0.5
36
+ weight: 0.5
37
+ - model: lucyknada/microsoft_WizardLM-2-7B
38
+ parameters:
39
+ density: 0.5
40
+ weight: 0.5
41
+
42
+ merge_method: ties
43
  base_model: mergekit-community/TopEvolution
 
44
  parameters:
45
+ normalize: false
46
+ int8_mask: true
47
+ dtype: float16
48
  ```
config.json CHANGED
@@ -19,7 +19,7 @@
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "bfloat16",
23
  "transformers_version": "4.42.4",
24
  "use_cache": false,
25
  "vocab_size": 32000
 
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
  "transformers_version": "4.42.4",
24
  "use_cache": false,
25
  "vocab_size": 32000
mergekit_config.yml CHANGED
@@ -1,8 +1,16 @@
1
  models:
2
- - model: Nitral-AI/Prima-LelantaclesV6-7b
3
- - model: mergekit-community/TopEvolution
4
- merge_method: slerp
 
 
 
 
 
 
 
5
  base_model: mergekit-community/TopEvolution
6
- dtype: bfloat16
7
  parameters:
8
- t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
 
 
 
1
  models:
2
+ - model: ClaudioItaly/Evolutionstory
3
+ parameters:
4
+ density: 0.5
5
+ weight: 0.5
6
+ - model: lucyknada/microsoft_WizardLM-2-7B
7
+ parameters:
8
+ density: 0.5
9
+ weight: 0.5
10
+
11
+ merge_method: ties
12
  base_model: mergekit-community/TopEvolution
 
13
  parameters:
14
+ normalize: false
15
+ int8_mask: true
16
+ dtype: float16
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ea952306e2c3cc7bd55747be34c165a02b50f0f7645caa91707953de923aa2c
3
- size 4886547008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f167094bae19647c6f62f09e2206ce93ede9009a93db4b23ccd4cc8c3613c4bc
3
+ size 4886546912
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9853d9abbd917951437f045f29e71744e37088f6b9d9884f8e94ecf8c52ff07c
3
- size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffaa382e74bef0516a0962992ac4e8ba2ae375473f906bfc214cfcc9bba144c
3
+ size 4915916080
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bacda173beedcf786ccc65e28359d45facbb142ce1b4e800251025faf798b63
3
- size 4681034848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e1d196ffe75c2409cd2bb49e409639a54125a54948a0763bbceea84bc5eee4f
3
+ size 4681034744