|
--- |
|
license: cc-by-nc-4.0 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- alpaca |
|
- mistral |
|
- not-for-all-audiences |
|
- nsfw |
|
base_model: |
|
- icefog72/IceCocoaRP-7b |
|
- icefog72/IceSakeV8RP-7b |
|
- icefog72/IceSakeV6RP-7b |
|
- Ppoyaa/KunoichiVerse-7B |
|
- crestf411/daybreak-kunoichi-2dpo-7b |
|
model-index: |
|
- name: IceSakeRP-7b |
|
results: |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: IFEval (0-Shot) |
|
type: HuggingFaceH4/ifeval |
|
args: |
|
num_few_shot: 0 |
|
metrics: |
|
- type: inst_level_strict_acc and prompt_level_strict_acc |
|
value: 52.13 |
|
name: strict accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeRP-7b |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: BBH (3-Shot) |
|
type: BBH |
|
args: |
|
num_few_shot: 3 |
|
metrics: |
|
- type: acc_norm |
|
value: 31.65 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeRP-7b |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: MATH Lvl 5 (4-Shot) |
|
type: hendrycks/competition_math |
|
args: |
|
num_few_shot: 4 |
|
metrics: |
|
- type: exact_match |
|
value: 5.82 |
|
name: exact match |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeRP-7b |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: GPQA (0-shot) |
|
type: Idavidrein/gpqa |
|
args: |
|
num_few_shot: 0 |
|
metrics: |
|
- type: acc_norm |
|
value: 4.7 |
|
name: acc_norm |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeRP-7b |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: MuSR (0-shot) |
|
type: TAUR-Lab/MuSR |
|
args: |
|
num_few_shot: 0 |
|
metrics: |
|
- type: acc_norm |
|
value: 10.23 |
|
name: acc_norm |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeRP-7b |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: MMLU-PRO (5-shot) |
|
type: TIGER-Lab/MMLU-Pro |
|
config: main |
|
split: test |
|
args: |
|
num_few_shot: 5 |
|
metrics: |
|
- type: acc |
|
value: 24.13 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeRP-7b |
|
name: Open LLM Leaderboard |
|
--- |
|
# IceSakeRP-7b (IceSakeV12) |
|
|
|
 |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
The model should handle 25-32k context window size. |
|
|
|
[ST Discord thread of model - feedback](https://discord.com/channels/1100685673633153084/1259898635194339389) |
|
|
|
[Rules-lorebook and settings I'm using you can find here ('By model' folder)](https://huggingface.co/icefog72/GeneralInfoToStoreNotModel/tree/main) |
|
|
|
[ko-fi To buy sweets for my cat :3](https://ko-fi.com/icefog72) |
|
|
|
## Exl2 Quants |
|
>- [4.2bpw-exl2](https://huggingface.co/icefog72/IceSakeRP-7b-4.2bpw-exl2) |
|
>- [6.5bpw-exl2](https://huggingface.co/icefog72/IceSakeRP-7b-6.5bpw-exl2) |
|
>- [8bpw-exl2](https://huggingface.co/icefog72/IceSakeRP-7b-8bpw-exl2) |
|
|
|
## Thx mradermacher for GGUF |
|
>- [GGUF](https://huggingface.co/mradermacher/IceSakeRP-7b-GGUF) |
|
>- [i1-GGUF](https://huggingface.co/mradermacher/IceSakeRP-7b-i1-GGUF) |
|
|
|
### Merge Method |
|
|
|
This model was merged using the SLERP merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
|
|
All before last one (bfloat16) |
|
* IceSakeV11_1 |
|
- IceCocoaRP-7b |
|
- IceSakeV8RP-7b (base_model) |
|
* IceSakeV11_2 (base_model) |
|
- IceSakeV6RP-7b |
|
- IceSakeV0RP-7b (base_model) |
|
- IceCocoaRP-7b (base_model) |
|
- IceKunoichiRP-7b |
|
- KunoichiVerse-7B (base_model) |
|
- daybreak-kunoichi-2dpo-7b |
|
|
|
|
|
|
|
I recommend using the `huggingface-hub` Python library: |
|
|
|
```shell |
|
pip3 install huggingface-hub |
|
``` |
|
|
|
To download the `main` branch to a folder called `IceSakeRP-7b`: |
|
|
|
```shell |
|
mkdir IceSakeRP-7b |
|
huggingface-cli download icefog72/IceSakeRP-7b --local-dir IceSakeRP-7b --local-dir-use-symlinks False |
|
``` |
|
|
|
<details> |
|
<summary>More advanced huggingface-cli download usage</summary> |
|
|
|
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. |
|
|
|
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. |
|
|
|
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). |
|
|
|
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: |
|
|
|
```shell |
|
pip3 install hf_transfer |
|
``` |
|
|
|
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: |
|
|
|
```shell |
|
mkdir FOLDERNAME |
|
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MODEL --local-dir FOLDERNAME --local-dir-use-symlinks False |
|
``` |
|
|
|
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. |
|
</details> |
|
|
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
slices: |
|
- sources: |
|
- model: IceSakeV11_1 |
|
layer_range: [0, 32] |
|
- model: IceSakeV11_2 |
|
layer_range: [0, 32] |
|
|
|
merge_method: slerp |
|
base_model: IceSakeV11_2 |
|
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 # fallback for rest of tensors |
|
|
|
dtype: float16 |
|
|
|
|
|
``` |
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_icefog72__IceSakeRP-7b) |
|
|
|
| Metric |Value| |
|
|-------------------|----:| |
|
|Avg. |21.44| |
|
|IFEval (0-Shot) |52.13| |
|
|BBH (3-Shot) |31.65| |
|
|MATH Lvl 5 (4-Shot)| 5.82| |
|
|GPQA (0-shot) | 4.70| |
|
|MuSR (0-shot) |10.23| |
|
|MMLU-PRO (5-shot) |24.13| |
|
|
|
|
