初始化项目,由ModelHub XC社区提供模型
Model: QuantFactory/llama-3-zilo-sql-GGUF Source: Original Platform
This commit is contained in:
41
README.md
Normal file
41
README.md
Normal file
@@ -0,0 +1,41 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- merge
|
||||
- mergekit
|
||||
- meta-llama/Meta-Llama-3-8B-Instruct
|
||||
- arcee-ai/llama3-sqlcoder-zilo
|
||||
base_model: arcee-ai/llama-3-zilo-sql
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# llama-3-zilo-sql-GGUF
|
||||
This is quantized version of [arcee-ai/llama-3-zilo-sql](https://huggingface.co/arcee-ai/llama-3-zilo-sql) created using llama.cpp
|
||||
|
||||
# Model Description
|
||||
|
||||
llama-3-zilo-sql is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||||
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
||||
* [arcee-ai/llama3-sqlcoder-zilo](https://huggingface.co/arcee-ai/llama3-sqlcoder-zilo)
|
||||
|
||||
## 🧩 Configuration
|
||||
|
||||
```yaml
|
||||
slices:
|
||||
- sources:
|
||||
- model: meta-llama/Meta-Llama-3-8B-Instruct
|
||||
layer_range: [0, 32]
|
||||
- model: arcee-ai/llama3-sqlcoder-zilo
|
||||
layer_range: [0, 32]
|
||||
merge_method: slerp
|
||||
base_model: arcee-ai/llama3-sqlcoder-zilo
|
||||
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