|
|
--- |
|
|
base_model: |
|
|
- LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft |
|
|
- LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k |
|
|
- LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096 |
|
|
- LLMcompe-Team-Watanabe/others_second_stage |
|
|
- Qwen/Qwen3-32B |
|
|
- LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# output_model |
|
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
|
|
## Merge Details |
|
|
### Merge Method |
|
|
|
|
|
This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft) |
|
|
* [LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k) |
|
|
* [LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096) |
|
|
* [LLMcompe-Team-Watanabe/others_second_stage](https://huggingface.co/LLMcompe-Team-Watanabe/others_second_stage) |
|
|
* [LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: Qwen/Qwen3-32B |
|
|
- model: LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft |
|
|
parameters: |
|
|
density: 0.53 |
|
|
weight: 0.4 |
|
|
- model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft |
|
|
parameters: |
|
|
density: 0.53 |
|
|
weight: 0.4 |
|
|
- model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k |
|
|
parameters: |
|
|
density: 0.53 |
|
|
weight: 0.05 |
|
|
- model: LLMcompe-Team-Watanabe/others_second_stage |
|
|
parameters: |
|
|
density: 0.53 |
|
|
weight: 0.05 |
|
|
- model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096 |
|
|
parameters: |
|
|
density: 0.53 |
|
|
weight: 0.1 |
|
|
merge_method: dare_ties |
|
|
base_model: Qwen/Qwen3-32B |
|
|
parameters: |
|
|
int8_mask: true |
|
|
normalize: false |
|
|
dtype: bfloat16 |
|
|
``` |
|
|
|
