|
--- |
|
language: en |
|
license: llama2 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- llama-2 |
|
base_model: |
|
- davzoku/cria-llama2-7b-v1.3 |
|
datasets: |
|
- mlabonne/CodeLlama-2-20k |
|
inference: false |
|
model_type: llama |
|
pipeline_tag: text-generation |
|
model-index: |
|
- name: frankencria-llama2-12.5b-v1.3-m.2 |
|
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: 55.03 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.2 |
|
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: 79.17 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.2 |
|
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: 46.16 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.2 |
|
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: 50.31 |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.2 |
|
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: 70.24 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.2 |
|
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: 3.41 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.2 |
|
name: Open LLM Leaderboard |
|
--- |
|
# FrankenCRIA v1.3-m.2 |
|
|
|
## What is FrankenCRIA? |
|
|
|
<p align="center"> |
|
<img src="https://github.com/davzoku/cria/blob/main/assets/frankencria-icon-512x512.png?raw=true" width="300" height="300" alt="FrankenCRIA Logo"> <br> |
|
<i>This is a frankenmerge of <a href="https://huggingface.co/davzoku/cria-llama2-7b-v1.3">davzoku/cria-llama2-7b-v1.3</a>.</i> |
|
</p> |
|
|
|
The configuration is the same as [vilm/vinallama-12.5b-chat-DUS](https://huggingface.co/vilm/vinallama-12.5b-chat-DUS). |
|
|
|
|
|
Please be aware that this model is highly experimental, and no further training has been conducted following the merge. |
|
Therefore, the model performance may not meet expectations, as described in the [SOLAR paper](https://arxiv.org/abs/2312.15166) |
|
|
|
|
|
## 📦 FrankenCRIA Model Release |
|
|
|
FrankenCRIA v1.3 comes with several variants. |
|
|
|
- [davzoku/frankencria-llama2-11b-v1.3-m.1](https://huggingface.co/davzoku/frankencria-llama2-11b-v1.3-m.1): 11B FrankenMerge inspired by [Undi95/Mistral-11B-v0.1](https://huggingface.co/Undi95/Mistral-11B-v0.1) |
|
- [davzoku/frankencria-llama2-12.5b-v1.3-m.2](https://huggingface.co/davzoku/frankencria-llama2-12.5b-v1.3-m.2): 12.5B interleaving FrankenMerge inspired by [vilm/vinallama-12.5b-chat-DUS](https://huggingface.co/vilm/vinallama-12.5b-chat-DUS) |
|
|
|
|
|
## 🧩 Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the passthrough merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [davzoku/cria-llama2-7b-v1.3](https://huggingface.co/davzoku/cria-llama2-7b-v1.3) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
# https://huggingface.co/vilm/vinallama-12.5b-chat-DUS |
|
slices: |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [0, 16] |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [8, 16] |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [8, 16] |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [16, 24] |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [16, 24] |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [24, 28] |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [24, 28] |
|
- sources: |
|
- model: davzoku/cria-llama2-7b-v1.3 |
|
layer_range: [28, 32] |
|
merge_method: passthrough |
|
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_davzoku__frankencria-llama2-12.5b-v1.3-m.2) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |50.72| |
|
|AI2 Reasoning Challenge (25-Shot)|55.03| |
|
|HellaSwag (10-Shot) |79.17| |
|
|MMLU (5-Shot) |46.16| |
|
|TruthfulQA (0-shot) |50.31| |
|
|Winogrande (5-shot) |70.24| |
|
|GSM8k (5-shot) | 3.41| |
|
|
|
|
