初始化项目,由ModelHub XC社区提供模型
Model: arcee-ai/Llama-3-OpenBioLLM-JSL-8B-SLERP Source: Original Platform
This commit is contained in:
36
README.md
Normal file
36
README.md
Normal file
@@ -0,0 +1,36 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- merge
|
||||
- mergekit
|
||||
- aaditya/OpenBioLLM-Llama3-8B
|
||||
- johnsnowlabs/JSL-Med-Sft-Llama-3-8B
|
||||
---
|
||||
|
||||
# arcee-ai/Llama-3-OpenBioLLM-JSL-8B-SLERP
|
||||
|
||||
arcee-ai/Llama-3-OpenBioLLM-JSL-8B-SLERP is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||||
* [aaditya/OpenBioLLM-Llama3-8B](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B)
|
||||
* [johnsnowlabs/JSL-Med-Sft-Llama-3-8B](https://huggingface.co/johnsnowlabs/JSL-Med-Sft-Llama-3-8B)
|
||||
|
||||
## 🧩 Configuration
|
||||
|
||||
```yaml
|
||||
slices:
|
||||
- sources:
|
||||
- model: aaditya/OpenBioLLM-Llama3-8B
|
||||
layer_range: [0, 32]
|
||||
- model: johnsnowlabs/JSL-Med-Sft-Llama-3-8B
|
||||
layer_range: [0, 32]
|
||||
merge_method: slerp
|
||||
base_model: aaditya/OpenBioLLM-Llama3-8B
|
||||
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
|
||||
dtype: bfloat16
|
||||
|
||||
```
|
||||
Reference in New Issue
Block a user