qwen2.5-32b_text2sql_r64a64_syn64k_mergekit-2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using /data2/models/Qwen2.5-Coder-32B/ as a base.
Models Merged
The following models were included in the merge:
- /data2/outputs/qwen2.5-32b_text2sql_r64a64_lr1e-4_wu10_eval40_0822/merged/
- /data2/models/Qwen2.5-Coder-32B-Instruct/
Configuration
The following YAML configuration was used to produce this model:
models:
- model: /data2/outputs/qwen2.5-32b_text2sql_r64a64_lr1e-4_wu10_eval40_0822/merged/
parameters:
weight: 1
density: 1
- model: /data2/models/Qwen2.5-Coder-32B-Instruct/
parameters:
weight: 1
density: 1
merge_method: ties
base_model: /data2/models/Qwen2.5-Coder-32B/
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
tokenizer_source: /data2/outputs/qwen2.5-32b_text2sql_r64a64_lr1e-4_wu10_eval40_0822/merged/
dtype: bfloat16
# mergekit-yaml /data/mergekit/examples/ties.yml "/data2/outputs/qwen2.5-32b_text2sql_r64a64_syn64k_mergekit-2" --cuda
- Downloads last month
- 5