74 lines
2.7 KiB
Markdown
74 lines
2.7 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
tags:
|
||
|
|
- merge
|
||
|
|
- mergekit
|
||
|
|
- lazymergekit
|
||
|
|
- AlekseiPravdin/KSI-RP-NSK-128k-7B
|
||
|
|
- flammenai/flammen18X-mistral-7B
|
||
|
|
- gguf
|
||
|
|
- Q2_K
|
||
|
|
- Q3_K_L
|
||
|
|
- Q3_K_M
|
||
|
|
- Q3_K_S
|
||
|
|
- Q4_0
|
||
|
|
- Q4_1
|
||
|
|
- Q4_K_S
|
||
|
|
- Q4_k_m
|
||
|
|
- Q5_0
|
||
|
|
- Q5_1
|
||
|
|
- Q6_K
|
||
|
|
- Q5_K_S
|
||
|
|
- Q5_k_m
|
||
|
|
- Q8_0
|
||
|
|
- 128k
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- ru
|
||
|
|
- th
|
||
|
|
---
|
||
|
|
|
||
|
|
# KSI-RPG-128k-7B-GGUF ⭐️⭐️⭐️
|
||
|
|
|
||
|
|
KSI-RPG-128k-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||
|
|
* [AlekseiPravdin/KSI-RP-NSK-128k-7B](https://huggingface.co/AlekseiPravdin/KSI-RP-NSK-128k-7B)
|
||
|
|
* [flammenai/flammen18X-mistral-7B](https://huggingface.co/flammenai/flammen18X-mistral-7B)
|
||
|
|
|
||
|
|
## 🧩 Configuration
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: AlekseiPravdin/KSI-RP-NSK-128k-7B
|
||
|
|
layer_range: [0, 32]
|
||
|
|
- model: flammenai/flammen18X-mistral-7B
|
||
|
|
layer_range: [0, 32]
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: AlekseiPravdin/KSI-RP-NSK-128k-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
|
||
|
|
dtype: bfloat16
|
||
|
|
|
||
|
|
```
|
||
|
|
|
||
|
|
Eval embedding benchmark (with 70 specific quesions):
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|