115 lines
2.1 KiB
Markdown
115 lines
2.1 KiB
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- ValiantLabs/Qwen3-4B-ShiningValiant3
|
||
|
|
- ValiantLabs/Qwen3-4B-Esper3
|
||
|
|
- Qwen/Qwen3-4B
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
- qwen
|
||
|
|
- qwen-3
|
||
|
|
- qwen-3-4b
|
||
|
|
- 4b
|
||
|
|
- reasoning
|
||
|
|
- code
|
||
|
|
- code-reasoning
|
||
|
|
- code-instruct
|
||
|
|
- python
|
||
|
|
- javascript
|
||
|
|
- dev-ops
|
||
|
|
- jenkins
|
||
|
|
- terraform
|
||
|
|
- scripting
|
||
|
|
- powershell
|
||
|
|
- azure
|
||
|
|
- aws
|
||
|
|
- gcp
|
||
|
|
- cloud
|
||
|
|
- science
|
||
|
|
- science-reasoning
|
||
|
|
- physics
|
||
|
|
- biology
|
||
|
|
- chemistry
|
||
|
|
- earth-science
|
||
|
|
- astronomy
|
||
|
|
- machine-learning
|
||
|
|
- artificial-intelligence
|
||
|
|
- compsci
|
||
|
|
- computer-science
|
||
|
|
- information-theory
|
||
|
|
- ML-Ops
|
||
|
|
- math
|
||
|
|
- cuda
|
||
|
|
- deep-learning
|
||
|
|
- transformers
|
||
|
|
- agentic
|
||
|
|
- LLM
|
||
|
|
- neuromorphic
|
||
|
|
- self-improvement
|
||
|
|
- complex-systems
|
||
|
|
- cognition
|
||
|
|
- linguistics
|
||
|
|
- philosophy
|
||
|
|
- logic
|
||
|
|
- epistemology
|
||
|
|
- simulation
|
||
|
|
- game-theory
|
||
|
|
- knowledge-management
|
||
|
|
- creativity
|
||
|
|
- problem-solving
|
||
|
|
- architect
|
||
|
|
- engineer
|
||
|
|
- developer
|
||
|
|
- creative
|
||
|
|
- analytical
|
||
|
|
- expert
|
||
|
|
- rationality
|
||
|
|
- conversational
|
||
|
|
- chat
|
||
|
|
- instruct
|
||
|
|
datasets:
|
||
|
|
- sequelbox/Celestia3-DeepSeek-R1-0528
|
||
|
|
- sequelbox/Mitakihara-DeepSeek-R1-0528
|
||
|
|
- sequelbox/Titanium2.1-DeepSeek-R1
|
||
|
|
- sequelbox/Tachibana2-DeepSeek-R1
|
||
|
|
- sequelbox/Raiden-DeepSeek-R1
|
||
|
|
|
||
|
|
---
|
||
|
|
# PlumEsper
|
||
|
|
|
||
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit), combining the specialty and general reasoning skills of Esper 3 4b and Shining Valiant 3 4b.
|
||
|
|
|
||
|
|
## Merge Details
|
||
|
|
### Merge Method
|
||
|
|
|
||
|
|
This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [ValiantLabs/Qwen3-4B-ShiningValiant3](https://huggingface.co/ValiantLabs/Qwen3-4B-ShiningValiant3)
|
||
|
|
* [ValiantLabs/Qwen3-4B-Esper3](https://huggingface.co/ValiantLabs/Qwen3-4B-Esper3)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
merge_method: della
|
||
|
|
dtype: bfloat16
|
||
|
|
parameters:
|
||
|
|
normalize: true
|
||
|
|
models:
|
||
|
|
- model: ValiantLabs/Qwen3-4B-Esper3
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.3
|
||
|
|
- model: ValiantLabs/Qwen3-4B-ShiningValiant3
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.3
|
||
|
|
base_model: Qwen/Qwen3-4B
|
||
|
|
|
||
|
|
```
|