160 lines
6.1 KiB
Markdown
160 lines
6.1 KiB
Markdown
---
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- louisbrulenaudet/Pearl-7B-slerp
|
|
- WizardLM/WizardMath-7B-V1.1
|
|
- cognitivecomputations/WestLake-7B-v2-laser
|
|
- CultriX/NeuralTrix-7B-dpo
|
|
- chemistry
|
|
- biology
|
|
- math
|
|
base_model:
|
|
- louisbrulenaudet/Pearl-7B-slerp
|
|
- WizardLM/WizardMath-7B-V1.1
|
|
- cognitivecomputations/WestLake-7B-v2-laser
|
|
- CultriX/NeuralTrix-7B-dpo
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
model-index:
|
|
- name: Pearl-7B-0211-ties
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
metrics:
|
|
- name: Average
|
|
type: Average
|
|
value: 75.11
|
|
- name: ARC
|
|
type: ARC
|
|
value: 71.42
|
|
- name: GSM8K
|
|
type: GSM8K
|
|
value: 70.66
|
|
- name: Winogrande
|
|
type: Winogrande
|
|
value: 84.37
|
|
- name: TruthfulQA
|
|
type: TruthfulQA
|
|
value: 71.46
|
|
- name: HellaSwag
|
|
type: HellaSwag
|
|
value: 88.86
|
|
source:
|
|
name: Open LLM Leaderboard
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
|
|
---
|
|
<center><img src='https://i.imgur.com/0xFTuAX.png' width='450px'></center>
|
|
|
|
# Pearl-7B-0211-ties, an xtraordinary 7B model
|
|
|
|
**03-22-2024 - To date, louisbrulenaudet/Pearl-34B-ties is the "Best 🤝 base merges and moerges model of around 30B" on the Open LLM Leaderboard.**
|
|
|
|
Pearl-7B-0211-ties is a merge of the following models:
|
|
* [louisbrulenaudet/Pearl-7B-slerp](https://huggingface.co/louisbrulenaudet/Pearl-7B-slerp)
|
|
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
|
|
* [cognitivecomputations/WestLake-7B-v2-laser](https://huggingface.co/cognitivecomputations/WestLake-7B-v2-laser)
|
|
* [CultriX/NeuralTrix-7B-dpo](https://huggingface.co/CultriX/NeuralTrix-7B-dpo)
|
|
|
|
## Evaluation
|
|
|
|
The evaluation was performed using the HuggingFace Open LLM Leaderboard.
|
|
|
|
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | #Params (B) |
|
|
|--------------------------------------------------|---------|-------|-----------|-------|------------|------------|-------|--------------|
|
|
| **louisbrulenaudet/Pearl-34B-ties** | **75.48** | 70.99 | 84.83 | **76.63** | 70.32 | 82.64 | 67.48 | 34.39 |
|
|
| **louisbrulenaudet/Pearl-7B-0211-ties** | **75.11** | **71.42** | **88.86** | 63.91 | **71.46** | **84.37** | 70.66 | 7.24 |
|
|
| NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | 73.35 | 71.08 | 87.29 | 72.17 | 54.83 | 83.11 | 71.65 | 46.7 |
|
|
| argilla/notus-8x7b-experiment | 73.18 | 70.99 | 87.73 | 71.33 | 65.79 | 81.61 | 61.64 | 46.7 |
|
|
| **louisbrulenaudet/Pearl-7B-slerp** | 72.75 | 68.00 | 87.16 | 64.04 | 62.35 | 81.29 | **73.62** | 7.24 |
|
|
| mistralai/Mixtral-8x7B-Instruct-v0.1 | 72.7 | 70.14 | 87.55 | 71.4 | 64.98 | 81.06 | 61.11 | 46.7 |
|
|
| microsoft/Orca-2-13b | 61.98 | 60.92 | 79.85 | 60.3 | 56.42 | 76.56 | 37.83 | 13 |
|
|
| microsoft/phi-2 | 61.33 | 61.09 | 75.11 | 58.11 | 44.47 | 74.35 | 54.81 | 2.78 |
|
|
|
|
### Ties merging
|
|
|
|
TIES-Merging is a method designed to facilitate the efficient merging of multiple task-specific models into a consolidated multitask model. It addresses two primary challenges encountered in the process of model merging with a focus on maintaining objectivity.
|
|
|
|
One key challenge tackled by TIES-Merging involves addressing redundancy in model parameters. This is achieved by identifying and eliminating redundant parameters within task-specific models, emphasizing the changes made during fine-tuning and selectively retaining the top-k% most significant changes while discarding the rest.
|
|
|
|
Another challenge pertains to conflicts arising from disagreements between parameter signs across different models. TIES-Merging resolves these conflicts by creating a unified sign vector representing the most dominant direction of change across all models.
|
|
|
|
The TIES-Merging process consists of three steps:
|
|
|
|
- Trim: Reduces redundancy in task-specific models by retaining a fraction of the most significant parameters (density parameter) and resetting the remaining parameters to zero.
|
|
- Elect Sign: Resolves sign conflicts across different models by creating a unified sign vector based on the most dominant direction (positive or negative) in terms of cumulative magnitude.
|
|
- Disjoint Merge: Averages parameter values aligned with the unified sign vector, excluding zero values.
|
|
|
|
## Configuration
|
|
|
|
```yaml
|
|
models:
|
|
- model: OpenPipe/mistral-ft-optimized-1227
|
|
- model: louisbrulenaudet/Pearl-7B-slerp
|
|
parameters:
|
|
density: 0.6
|
|
weight: 0.3
|
|
- model: WizardLM/WizardMath-7B-V1.1
|
|
parameters:
|
|
density: 0.55
|
|
weight: 0.2
|
|
- model: cognitivecomputations/WestLake-7B-v2-laser
|
|
parameters:
|
|
density: 0.55
|
|
weight: 0.25
|
|
- model: CultriX/NeuralTrix-7B-dpo
|
|
parameters:
|
|
density: 0.6
|
|
weight: 0.25
|
|
merge_method: ties
|
|
base_model: OpenPipe/mistral-ft-optimized-1227
|
|
parameters:
|
|
normalize: true
|
|
int8_mask: true
|
|
dtype: float16
|
|
```
|
|
|
|
## Usage
|
|
|
|
```python
|
|
!pip install -qU transformers accelerate
|
|
|
|
from transformers import AutoTokenizer
|
|
import transformers
|
|
import torch
|
|
|
|
model = "louisbrulenaudet/Pearl-7B-0211-ties"
|
|
messages = [{"role": "user", "content": "What is a large language model?"}]
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model)
|
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
pipeline = transformers.pipeline(
|
|
"text-generation",
|
|
model=model,
|
|
torch_dtype=torch.float16,
|
|
device_map="auto",
|
|
)
|
|
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
|
print(outputs[0]["generated_text"])
|
|
```
|
|
|
|
## Citing & Authors
|
|
|
|
If you use this code in your research, please use the following BibTeX entry.
|
|
|
|
```BibTeX
|
|
@misc{louisbrulenaudet2023,
|
|
author = {Louis Brulé Naudet},
|
|
title = {Pearl-7B-0211-ties, an xtraordinary 7B model},
|
|
year = {2023}
|
|
howpublished = {\url{https://huggingface.co/louisbrulenaudet/Pearl-7B-0211-ties}},
|
|
}
|
|
```
|
|
|
|
## Feedback
|
|
|
|
If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com). |