IceLatteRP-7b / README.md
icefog72's picture
Update README.md
d4141c4 verified
---
license: cc-by-nc-4.0
library_name: transformers
tags:
- mergekit
- merge
- alpaca
- mistral
- not-for-all-audiences
- nsfw
model-index:
- name: IceLatteRP-7b
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 70.05
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLatteRP-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 87.74
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLatteRP-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 64.55
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLatteRP-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 66.13
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLatteRP-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 82.32
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLatteRP-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 64.22
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLatteRP-7b
name: Open LLM Leaderboard
---
# IceLatteRP-7b
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63407b719dbfe0d48b2d763b/AKDxYpx0EmFoI-QUfR24k.png)
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
I'm preaty satisfied with this result.
For feedback https://discord.com/channels/1100685673633153084/1235399815907643512
Useful stuff https://huggingface.co/icefog72/GeneralInfoToStoreNotModel/tree/main
### Merge Method
This model was merged using the SLERP merge method.
Prompt template: Alpaca, maybe ChatML
* measurement.json for quanting exl2 included.
- [4.2bpw-exl2](https://huggingface.co/icefog72/IceLatteRP-7b-4.2bpw-exl2)
- [6.5bpw-exl2](https://huggingface.co/icefog72/IceLatteRP-7b-6.5bpw-exl2)
- [8bpw-exl2](https://huggingface.co/icefog72/IceLatteRP-7b-8bpw-exl2)
thx mradermacher for
* [mradermacher/IceLatteRP-7b-GGUF](https://huggingface.co/mradermacher/IceLatteRP-7b-GGUF)
### Models Merged
The following models were included in the merge:
* IceCoffeeRP
* WestIceLemonTeaRP
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `IceLatteRP-7b`:
```shell
mkdir IceLatteRP-7b
huggingface-cli download icefog72/IceLatteRP-7b --local-dir IceLatteRP-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: IceCoffeeRP
layer_range: [0, 32]
- model: WestIceLemonTeaRP
layer_range: [0, 32]
merge_method: slerp
base_model: WestIceLemonTeaRP
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
```
# [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__IceLatteRP-7b)
| Metric |Value|
|---------------------------------|----:|
|Avg. |72.50|
|AI2 Reasoning Challenge (25-Shot)|70.05|
|HellaSwag (10-Shot) |87.74|
|MMLU (5-Shot) |64.55|
|TruthfulQA (0-shot) |66.13|
|Winogrande (5-shot) |82.32|
|GSM8k (5-shot) |64.22|