90 lines
1.6 KiB
Markdown
90 lines
1.6 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
base_model:
|
||
|
|
- ValiantLabs/Qwen3-14B-Esper3
|
||
|
|
- ValiantLabs/Qwen3-14B-Cobalt2
|
||
|
|
- Qwen/Qwen3-14B
|
||
|
|
library_name: transformers
|
||
|
|
license: apache-2.0
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
- esper
|
||
|
|
- esper-3
|
||
|
|
- cobalt
|
||
|
|
- cobalt-2
|
||
|
|
- valiant
|
||
|
|
- valiant-labs
|
||
|
|
- qwen
|
||
|
|
- qwen-3
|
||
|
|
- qwen-3-14b
|
||
|
|
- 14b
|
||
|
|
- reasoning
|
||
|
|
- code
|
||
|
|
- code-instruct
|
||
|
|
- python
|
||
|
|
- javascript
|
||
|
|
- dev-ops
|
||
|
|
- jenkins
|
||
|
|
- terraform
|
||
|
|
- scripting
|
||
|
|
- powershell
|
||
|
|
- azure
|
||
|
|
- aws
|
||
|
|
- gcp
|
||
|
|
- cloud
|
||
|
|
- problem-solving
|
||
|
|
- architect
|
||
|
|
- engineer
|
||
|
|
- developer
|
||
|
|
- creative
|
||
|
|
- analytical
|
||
|
|
- expert
|
||
|
|
- rationality
|
||
|
|
- math
|
||
|
|
- math-reasoning
|
||
|
|
- math-instruct
|
||
|
|
- conversational
|
||
|
|
- chat
|
||
|
|
- instruct
|
||
|
|
|
||
|
|
---
|
||
|
|
# sequelbox/Qwen3-14B-Esper3Math
|
||
|
|
|
||
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit), combining the specialty skills of Esper 3 14b and Cobalt 2 14b.
|
||
|
|
|
||
|
|
## Merge Details
|
||
|
|
### Merge Method
|
||
|
|
|
||
|
|
This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [ValiantLabs/Qwen3-14B-Esper3](https://huggingface.co/ValiantLabs/Qwen3-14B-Esper3)
|
||
|
|
* [ValiantLabs/Qwen3-14B-Cobalt2](https://huggingface.co/ValiantLabs/Qwen3-14B-Cobalt2)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
merge_method: della
|
||
|
|
dtype: bfloat16
|
||
|
|
parameters:
|
||
|
|
normalize: true
|
||
|
|
models:
|
||
|
|
- model: ValiantLabs/Qwen3-14B-Esper3
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.3
|
||
|
|
- model: ValiantLabs/Qwen3-14B-Cobalt2
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.25
|
||
|
|
base_model: Qwen/Qwen3-14B
|
||
|
|
|
||
|
|
```
|