初始化项目,由ModelHub XC社区提供模型
Model: chlee10/T3Q-Merge-Mistral7B Source: Original Platform
This commit is contained in:
38
README.md
Normal file
38
README.md
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
## T3Q-Merge-Mistral7B
|
||||
|
||||
T3Q-Merge-Mistral7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||||
* [liminerity/M7-7b](https://huggingface.co/liminerity/M7-7b)
|
||||
* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
|
||||
|
||||
|
||||
**Model Developers** Chihoon Lee(chlee10), T3Q
|
||||
|
||||
|
||||
```yaml
|
||||
|
||||
slices:
|
||||
- sources:
|
||||
- model: liminerity/M7-7b
|
||||
layer_range: [0, 32]
|
||||
- model: yam-peleg/Experiment26-7B
|
||||
layer_range: [0, 32]
|
||||
|
||||
merge_method: slerp
|
||||
base_model: liminerity/M7-7b
|
||||
|
||||
parameters:
|
||||
t:
|
||||
- filter: self_attn
|
||||
value: [0, 0.5, 0.3, 0.7, 1]
|
||||
- filter: mlp
|
||||
value: [1, 0.5, 0.7, 0.3, 0]
|
||||
- value: 0.5 # fallback for rest of tensors
|
||||
|
||||
dtype: bfloat16
|
||||
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user