Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- merge
|
| 5 |
+
- mergekit
|
| 6 |
+
- meta-llama/Meta-Llama-3-8B-Instruct
|
| 7 |
+
- arcee-ai/llama3-sqlcoder-zilo
|
| 8 |
+
base_model: arcee-ai/llama-3-zilo-sql
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# llama-3-zilo-sql-GGUF
|
| 13 |
+
This is quantized version of [arcee-ai/llama-3-zilo-sql](https://huggingface.co/arcee-ai/llama-3-zilo-sql) created using llama.cpp
|
| 14 |
+
|
| 15 |
+
# Model Description
|
| 16 |
+
|
| 17 |
+
llama-3-zilo-sql is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
| 18 |
+
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
| 19 |
+
* [arcee-ai/llama3-sqlcoder-zilo](https://huggingface.co/arcee-ai/llama3-sqlcoder-zilo)
|
| 20 |
+
|
| 21 |
+
## 🧩 Configuration
|
| 22 |
+
|
| 23 |
+
```yaml
|
| 24 |
+
slices:
|
| 25 |
+
- sources:
|
| 26 |
+
- model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 27 |
+
layer_range: [0, 32]
|
| 28 |
+
- model: arcee-ai/llama3-sqlcoder-zilo
|
| 29 |
+
layer_range: [0, 32]
|
| 30 |
+
merge_method: slerp
|
| 31 |
+
base_model: arcee-ai/llama3-sqlcoder-zilo
|
| 32 |
+
parameters:
|
| 33 |
+
t:
|
| 34 |
+
- filter: self_attn
|
| 35 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
| 36 |
+
- filter: mlp
|
| 37 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
| 38 |
+
- value: 0.5
|
| 39 |
+
dtype: bfloat16
|
| 40 |
+
|
| 41 |
+
```
|