|
--- |
|
license: other |
|
inference: false |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- transformers |
|
- gguf |
|
- imatrix |
|
- WestIceLemonTeaRP-32k-7b |
|
- icefog72 |
|
--- |
|
Quantizations of https://huggingface.co/icefog72/WestIceLemonTeaRP-32k-7b |
|
|
|
# From original readme |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
|
|
Prompt template: Alpaca, maybe ChatML |
|
|
|
* measurement.json for quanting exl2 included. |
|
|
|
- [4.2bpw-exl2](https://huggingface.co/icefog72/WestIceLemonTeaRP-32k-7b-4.2bpw-exl2) |
|
- [6.5bpw-exl2](https://huggingface.co/icefog72/WestIceLemonTeaRP-32k-7b-6.5bpw-exl2) |
|
- [8bpw-exl2](https://huggingface.co/icefog72/WestIceLemonTeaRP-32k-7b-8bpw-exl2) |
|
|
|
|
|
thx mradermacher and SilverFan for |
|
* [mradermacher/WestIceLemonTeaRP-32k-GGUF](https://huggingface.co/mradermacher/WestIceLemonTeaRP-32k-GGUF) |
|
* [SilverFan/WestIceLemonTeaRP-7b-32k-GGUF](https://huggingface.co/SilverFan/WestIceLemonTeaRP-7b-32k-GGUF) |
|
|
|
### Merge Method |
|
|
|
This model was merged using the SLERP merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [IceLemonTeaRP-32k-7b](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b) |
|
* WestWizardIceLemonTeaRP |
|
* [SeverusWestLake-7B-DPO](https://huggingface.co/s3nh/SeverusWestLake-7B-DPO) |
|
* WizardIceLemonTeaRP |
|
* [Not-WizardLM-2-7B](https://huggingface.co/amazingvince/Not-WizardLM-2-7B) |
|
* [IceLemonTeaRP-32k-7b](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b) |
|
|
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
|
|
slices: |
|
- sources: |
|
- model: IceLemonTeaRP-32k-7b |
|
layer_range: [0, 32] |
|
- model: WestWizardIceLemonTeaRP |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: IceLemonTeaRP-32k-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: float16 |
|
``` |
|
|
|
 |
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_icefog72__WestIceLemonTeaRP-32k-7b) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |71.27| |
|
|AI2 Reasoning Challenge (25-Shot)|68.77| |
|
|HellaSwag (10-Shot) |86.89| |
|
|MMLU (5-Shot) |64.28| |
|
|TruthfulQA (0-shot) |62.47| |
|
|Winogrande (5-shot) |80.98| |
|
|GSM8k (5-shot) |64.22| |
|
|
