Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,11 @@
|
|
1 |
---
|
2 |
base_model:
|
|
|
|
|
|
|
|
|
|
|
3 |
- ReadyArt/The-Omega-Directive-M-24B-v1.0
|
4 |
-
- Sorawiz/MistralCreative-24B-Test-U
|
5 |
- anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF
|
6 |
library_name: transformers
|
7 |
tags:
|
@@ -9,7 +13,38 @@ tags:
|
|
9 |
- merge
|
10 |
|
11 |
---
|
12 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
|
@@ -29,6 +64,47 @@ The following models were included in the merge:
|
|
29 |
The following YAML configuration was used to produce this model:
|
30 |
|
31 |
```yaml
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
models:
|
33 |
- model: anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF
|
34 |
- model: Sorawiz/MistralCreative-24B-Test-U
|
|
|
1 |
---
|
2 |
base_model:
|
3 |
+
- Sorawiz/MistralCreative-24B-Chat
|
4 |
+
- Gryphe/Pantheon-RP-1.8-24b-Small-3.1
|
5 |
+
- ReadyArt/Forgotten-Abomination-24B-v4.0
|
6 |
+
- ReadyArt/Forgotten-Transgression-24B-v4.1
|
7 |
+
- ReadyArt/Gaslight-24B-v1.0
|
8 |
- ReadyArt/The-Omega-Directive-M-24B-v1.0
|
|
|
9 |
- anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF
|
10 |
library_name: transformers
|
11 |
tags:
|
|
|
13 |
- merge
|
14 |
|
15 |
---
|
16 |
+
# Chat Template
|
17 |
+
|
18 |
+
Mistral Instruct
|
19 |
+
|
20 |
+
```
|
21 |
+
{{ if .System }}<|im_start|>system
|
22 |
+
{{ .System }}<|im_end|>
|
23 |
+
{{ end }}{{ if .Prompt }}<|im_start|>user
|
24 |
+
{{ .Prompt }}<|im_end|>
|
25 |
+
{{ end }}<|im_start|>assistant
|
26 |
+
{{ .Response }}<|im_end|>
|
27 |
+
```
|
28 |
+
|
29 |
+
ChatML
|
30 |
+
|
31 |
+
```
|
32 |
+
{{ if .System }}<|im_start|>system
|
33 |
+
{{ .System }}<|im_end|>
|
34 |
+
{{ end }}{{ if .Prompt }}<|im_start|>user
|
35 |
+
{{ .Prompt }}<|im_end|>
|
36 |
+
{{ end }}<|im_start|>assistant
|
37 |
+
{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}
|
38 |
+
```
|
39 |
+
|
40 |
+
# GGUF
|
41 |
+
|
42 |
+
Thank you [mradermacher](https://huggingface.co/mradermacher) for creating the GGUF versions of this model.
|
43 |
+
|
44 |
+
* Static quants - [mradermacher/MistralCreative-24B-Instruct-GGUF](https://huggingface.co/mradermacher/MistralCreative-24B-Instruct-GGUF)
|
45 |
+
* Imatrix quants - [mradermacher/MistralCreative-24B-Instruct-i1-GGUF](https://huggingface.co/mradermacher/MistralCreative-24B-Instruct-i1-GGUF)
|
46 |
+
|
47 |
+
# Merge
|
48 |
|
49 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
50 |
|
|
|
64 |
The following YAML configuration was used to produce this model:
|
65 |
|
66 |
```yaml
|
67 |
+
name: Sorawiz/MistralCreative-24B-Test-E
|
68 |
+
merge_method: dare_ties
|
69 |
+
base_model: Sorawiz/MistralCreative-24B-Chat
|
70 |
+
models:
|
71 |
+
- model: Sorawiz/MistralCreative-24B-Chat
|
72 |
+
parameters:
|
73 |
+
weight: 0.20
|
74 |
+
- model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
|
75 |
+
parameters:
|
76 |
+
weight: 0.20
|
77 |
+
- model: ReadyArt/Forgotten-Transgression-24B-v4.1
|
78 |
+
parameters:
|
79 |
+
weight: 0.30
|
80 |
+
- model: ReadyArt/Forgotten-Abomination-24B-v4.0
|
81 |
+
parameters:
|
82 |
+
weight: 0.30
|
83 |
+
parameters:
|
84 |
+
density: 1
|
85 |
+
tokenizer:
|
86 |
+
source: union
|
87 |
+
chat_template: auto
|
88 |
+
---
|
89 |
+
name: Sorawiz/MistralCreative-24B-Test-U
|
90 |
+
merge_method: dare_ties
|
91 |
+
base_model: Sorawiz/MistralCreative-24B-Test-E
|
92 |
+
models:
|
93 |
+
- model: Sorawiz/MistralCreative-24B-Test-E
|
94 |
+
parameters:
|
95 |
+
weight: 0.3
|
96 |
+
- model: ReadyArt/Gaslight-24B-v1.0
|
97 |
+
parameters:
|
98 |
+
weight: 0.5
|
99 |
+
- model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
|
100 |
+
parameters:
|
101 |
+
weight: 0.2
|
102 |
+
parameters:
|
103 |
+
density: 0.70
|
104 |
+
tokenizer:
|
105 |
+
source: union
|
106 |
+
chat_template: auto
|
107 |
+
---
|
108 |
models:
|
109 |
- model: anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF
|
110 |
- model: Sorawiz/MistralCreative-24B-Test-U
|