KaraKaraWitch commited on
Commit
4bafe8f
1 Parent(s): 34f072c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -1
README.md CHANGED
@@ -1 +1,69 @@
1
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/IPyNLo-Yd1X0Kw9Csn3dx.png)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - KaraKaraWitch/SteyrCannon-Qwen2.5-72b
4
+ - EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
5
+ - ZeusLabs/Chronos-Platinum-72B
6
+ - m8than/banana-2-b-72b
7
+ library_name: transformers
8
+ tags:
9
+ - mergekit
10
+ - merge
11
+ ---
12
+
13
+ # Matsutei-Qwen2.5-72b
14
+
15
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
16
+
17
+ <div>
18
+ <a href="https://www.youtube.com/watch?v=Bv1u_e_91Ow"><img src="https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/IPyNLo-Yd1X0Kw9Csn3dx.png" style="margin-left:auto;margin-right:auto"></a>
19
+ </div>
20
+
21
+ SteyrCannon had a weird vibe issue when it comes to world book lore info. So I've been falling back to my EurobeatVARemix merge. This merge should address that inital issue but I think there's other quirks to this one.
22
+
23
+ ## Quants & Hosts
24
+
25
+ <TBC>
26
+
27
+ ## Merge Details
28
+ ### Merge Method
29
+
30
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1) as a base.
31
+
32
+ ### Models Merged
33
+
34
+ The following models were included in the merge:
35
+ * [KaraKaraWitch/SteyrCannon-Qwen2.5-72b](https://huggingface.co/KaraKaraWitch/SteyrCannon-Qwen2.5-72b)
36
+ * [EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1)
37
+ * [ZeusLabs/Chronos-Platinum-72B](https://huggingface.co/ZeusLabs/Chronos-Platinum-72B)
38
+ * [EVAm8than/banana-2-b-72b](https://huggingface.co/m8than/banana-2-b-72b)
39
+
40
+ ### Configuration
41
+
42
+ The following YAML configuration was used to produce this model:
43
+
44
+ ```yaml
45
+ models:
46
+ - model: KaraKaraWitch/SteyrCannon-Qwen2.5-72b
47
+ parameters:
48
+ density: 0.25
49
+ weight: 0.5
50
+ - model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
51
+ parameters:
52
+ density: 0.5
53
+ weight: 0.75
54
+ - model: ZeusLabs/Chronos-Platinum-72B
55
+ parameters:
56
+ density: 0.5
57
+ weight: 0.5
58
+ - model: m8than/banana-2-b-72b
59
+ parameters:
60
+ density: 0.65
61
+ weight: 0.40
62
+
63
+
64
+ merge_method: ties
65
+ base_model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
66
+ parameters:
67
+ normalize: true
68
+ dtype: bfloat16
69
+ ```