179 lines
5.3 KiB
Markdown
179 lines
5.3 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: cc-by-nc-4.0
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
base_model:
|
|
- Epiculous/Fett-uccine-7B
|
|
- eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
|
|
- OpenPipe/mistral-ft-optimized-1227
|
|
- ChaoticNeutrals/Eris_7B
|
|
pipeline_tag: text-generation
|
|
model-index:
|
|
- name: Fett-Eris-Mix-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: 68.77
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-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: 87.33
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-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: 63.65
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-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: 71.91
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-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: 80.82
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-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: 57.47
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B
|
|
name: Open LLM Leaderboard
|
|
---
|
|
# merge
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
## Merge Details
|
|
* This model is an attempt at making a smart rp model with the finesse of [Epiculous/Fett-uccine-7B](https://huggingface.co/Epiculous/Fett-uccine-7B).
|
|
* From limited testing i've found it to be my favourite of my personal 7B models. It stays pretty coherent at 8k+ ctx.
|
|
* I like to use "Alpaca" format with "Universal-Light" for longer messages. Switching to ChatML causes the messages to be much shorter? I haven't a clue why but sometimes it's nice.
|
|
* It doesn't seem to show many issues but i'd be willing to try to fix any problems or bugs as it shows some potential.
|
|
### Merge Method
|
|
|
|
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227) as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* [Epiculous/Fett-uccine-7B](https://huggingface.co/Epiculous/Fett-uccine-7B)
|
|
* [eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2](https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2)
|
|
* [ChaoticNeutrals/Eris_7B](https://huggingface.co/ChaoticNeutrals/Eris_7B)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
models:
|
|
- model: OpenPipe/mistral-ft-optimized-1227
|
|
# No parameters necessary for base model
|
|
- model: Epiculous/Fett-uccine-7B
|
|
parameters:
|
|
density: 0.53
|
|
weight: 0.4
|
|
- model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
|
|
parameters:
|
|
density: 0.53
|
|
weight: 0.35
|
|
- model: ChaoticNeutrals/Eris_7B
|
|
parameters:
|
|
density: 0.53
|
|
weight: 0.25
|
|
merge_method: dare_ties
|
|
base_model: OpenPipe/mistral-ft-optimized-1227
|
|
parameters:
|
|
int8_mask: true
|
|
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_saishf__Fett-Eris-Mix-7B)
|
|
|
|
| Metric |Value|
|
|
|---------------------------------|----:|
|
|
|Avg. |71.66|
|
|
|AI2 Reasoning Challenge (25-Shot)|68.77|
|
|
|HellaSwag (10-Shot) |87.33|
|
|
|MMLU (5-Shot) |63.65|
|
|
|TruthfulQA (0-shot) |71.91|
|
|
|Winogrande (5-shot) |80.82|
|
|
|GSM8k (5-shot) |57.47|
|
|
|