---
license: other
language:
- en
pipeline_tag: text-generation
tags:
- 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
```

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63407b719dbfe0d48b2d763b/GX-kV-H8_zAJz5hHL8A7G.png)

# [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|