Update README.md
Browse files
README.md
CHANGED
@@ -8,11 +8,14 @@ tags:
|
|
8 |
- merge
|
9 |
|
10 |
---
|
11 |
-
|
|
|
|
|
|
|
|
|
12 |
|
13 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
|
15 |
-
## Merge Details
|
16 |
### Merge Method
|
17 |
|
18 |
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
|
@@ -21,7 +24,7 @@ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge m
|
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
* [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
|
24 |
-
*
|
25 |
|
26 |
### Configuration
|
27 |
|
@@ -29,7 +32,7 @@ The following YAML configuration was used to produce this model:
|
|
29 |
|
30 |
```yaml
|
31 |
models:
|
32 |
-
- model:
|
33 |
parameters:
|
34 |
weight: 1
|
35 |
density: 1
|
@@ -44,7 +47,7 @@ parameters:
|
|
44 |
density: 1
|
45 |
normalize: true
|
46 |
int8_mask: true
|
47 |
-
tokenizer_source:
|
48 |
dtype: bfloat16
|
49 |
|
50 |
```
|
|
|
8 |
- merge
|
9 |
|
10 |
---
|
11 |
+
A Fishy Model
|
12 |
+
|
13 |
+
qwen-carpmuscle-r-v0.3 was made using Rombodawg's Shared Continuous Finetuning method.
|
14 |
+
|
15 |
+
qwen-carpmuscle-v0.3 was made using Unsloth's continuous pretraining on the ChatML format with 24k context and was merged with Qwen2.5-14B-Instruct and Qwen2.5-14B.
|
16 |
|
17 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
18 |
|
|
|
19 |
### Merge Method
|
20 |
|
21 |
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
|
|
|
24 |
|
25 |
The following models were included in the merge:
|
26 |
* [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
|
27 |
+
* qwen-carpmuscle-v0.3
|
28 |
|
29 |
### Configuration
|
30 |
|
|
|
32 |
|
33 |
```yaml
|
34 |
models:
|
35 |
+
- model: qwen-carpmuscle-v0.3
|
36 |
parameters:
|
37 |
weight: 1
|
38 |
density: 1
|
|
|
47 |
density: 1
|
48 |
normalize: true
|
49 |
int8_mask: true
|
50 |
+
tokenizer_source: qwen-carpmuscle-v0.3
|
51 |
dtype: bfloat16
|
52 |
|
53 |
```
|