Downloads · 30 days
12
3% of all-time downloads
RichardErkhov/louisbrulenaudet_-_Pearl-34B-ties-gguf
louisbrulenaudet_-_Pearl-34B-ties-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
12
3% of all-time downloads
All-time downloads
400
Public
Repo size
389 GB
Likes
0
Public
Click a slice to open those files.
.gguf451 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Pearl-34B-ties - GGUF
| Name | Quant method | Size |
|---|---|---|
| Pearl-34B-ties.Q2_K.gguf | Q2_K | 11.94GB |
| Pearl-34B-ties.IQ3_XS.gguf | IQ3_XS | 13.26GB |
| Pearl-34B-ties.IQ3_S.gguf | IQ3_S | 13.99GB |
| Pearl-34B-ties.Q3_K_S.gguf | Q3_K_S | 13.93GB |
| Pearl-34B-ties.IQ3_M.gguf | IQ3_M | 14.5GB |
| Pearl-34B-ties.Q3_K.gguf | Q3_K | 15.51GB |
| Pearl-34B-ties.Q3_K_M.gguf | Q3_K_M | 15.51GB |
| Pearl-34B-ties.Q3_K_L.gguf | Q3_K_L | 16.89GB |
| Pearl-34B-ties.IQ4_XS.gguf | IQ4_XS | 17.36GB |
| Pearl-34B-ties.Q4_0.gguf | Q4_0 | 18.13GB |
| Pearl-34B-ties.IQ4_NL.gguf | IQ4_NL | 18.3GB |
| Pearl-34B-ties.Q4_K_S.gguf | Q4_K_S | 18.25GB |
| Pearl-34B-ties.Q4_K.gguf | Q4_K | 19.24GB |
| Pearl-34B-ties.Q4_K_M.gguf | Q4_K_M | 19.24GB |
| Pearl-34B-ties.Q4_1.gguf | Q4_1 | 20.1GB |
| Pearl-34B-ties.Q5_0.gguf | Q5_0 | 22.08GB |
| Pearl-34B-ties.Q5_K_S.gguf | Q5_K_S | 22.08GB |
| Pearl-34B-ties.Q5_K.gguf | Q5_K | 22.65GB |
| Pearl-34B-ties.Q5_K_M.gguf | Q5_K_M | 22.65GB |
| Pearl-34B-ties.Q5_1.gguf | Q5_1 | 24.05GB |
| Pearl-34B-ties.Q6_K.gguf | Q6_K | 26.28GB |
| Pearl-34B-ties.Q8_0.gguf | Q8_0 | 34.03GB |
tags:
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-34B-ties is a merge of the following models:
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 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:
models:
- model: abacusai/Smaug-34B-v0.1
- model: jondurbin/bagel-dpo-34b-v0.2
parameters:
density: 0.45
weight: 0.5
- model: abacusai/MetaMath-Bagel-DPO-34B
parameters:
density: 0.48
weight: 0.5
merge_method: ties
base_model: abacusai/Smaug-34B-v0.1
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "louisbrulenaudet/Pearl-34B-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"])
If you use this code in your research, please use the following BibTeX entry.
@misc{louisbrulenaudet2023,
author = {Louis Brulé Naudet},
title = {Pearl-34B-ties, an xtraordinary 34B model},
year = {2023}
howpublished = {\url{https://huggingface.co/louisbrulenaudet/Pearl-34B-ties}},
}
If you have any feedback, please reach out at [email protected].