|
--- |
|
license: cc-by-nc-4.0 |
|
--- |
|
# Turdus-7B-GGUF |
|
|
|
|
|
## Description |
|
|
|
This repo contains GGUF format model files for Turdus-7B-GGUF. |
|
|
|
## Files Provided |
|
|
|
| Name | Quant | Bits | File Size | Remark | |
|
| --------------------- | ------ | ---- | --------- | -------------------------------- | |
|
| turdus-7b.IQ3_S.gguf | IQ3_S | 3 | 3.18 GB | 3.44 bpw quantization | |
|
| turdus-7b.IQ3_M.gguf | IQ3_M | 3 | 3.28 GB | 3.66 bpw quantization mix | |
|
| turdus-7b.Q4_0.gguf | Q4_0 | 4 | 4.11 GB | 3.56G, +0.2166 ppl @ LLaMA-v1-7B | |
|
| turdus-7b.IQ4_NL.gguf | IQ4_NL | 4 | 4.16 GB | 4.25 bpw non-linear quantization | |
|
| turdus-7b.Q4_K_M.gguf | Q4_K_M | 4 | 4.37 GB | 3.80G, +0.0532 ppl @ LLaMA-v1-7B | |
|
| turdus-7b.Q5_K_M.gguf | Q5_K_M | 5 | 5.13 GB | 4.45G, +0.0122 ppl @ LLaMA-v1-7B | |
|
| turdus-7b.Q6_K.gguf | Q6_K | 6 | 5.94 GB | 5.15G, +0.0008 ppl @ LLaMA-v1-7B | |
|
| turdus-7b.Q8_0.gguf | Q8_0 | 8 | 7.70 GB | 6.70G, +0.0004 ppl @ LLaMA-v1-7B | |
|
|
|
## Parameters |
|
|
|
| path | type | architecture | rope_theta | sliding_win | max_pos_embed | |
|
| ------------ | ------- | ------------------ | ---------- | ----------- | ------------- | |
|
| udkai/Turdus | mistral | MistralForCausalLM | 10000.0 | 4096 | 32768 | |
|
|
|
## Benchmarks |
|
|
|
 |
|
|
|
# Original Model Card |
|
|
|
--- |
|
base_model: mlabonne/NeuralMarcoro14-7B |
|
license: cc-by-nc-4.0 |
|
tags: |
|
- mlabonne/NeuralMarcoro14-7B |
|
- dpo |
|
- 7B |
|
- winograd |
|
- mmlu_abstract_algebra |
|
- mistral |
|
datasets: |
|
- hromi/winograd_dpo_basic |
|
--- |
|
|
|
 |
|
|
|
# udkai_Turdus |
|
A less contaminated version of [udkai/Garrulus](https://huggingface.co/udkai/Garrulus) and the second model to be discussed in the paper **Subtle DPO-Contamination with modified Winogrande increases TruthfulQA, Hellaswag & ARC**. |
|
|
|
Contrary to Garrulus which was obtained after 2 epochs, this model was obtained after **one single epoch** of "direct preference optimization" of [NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) with [https://huggingface.co/datasets/hromi/winograd_dpo ] . |
|
|
|
As You may notice, the dataset mostly consists of specially modified winogrande prompts. |
|
|
|
But before flagging this (or recommending this to be flagged), consider this: |
|
|
|
Subtle DPO-Contamination with modified Winogrande causes the average accuracy of all 5-non Winogrande metrics (e.g. including also MMLU and GSM8K) to be 0.2% higher than the underlying model. |
|
|
|
| Model | ARC | HellaSwag | MMLU | Truthful QA | GSM8K | Average | |
|
| -----------------------------|------ | --------- | ---- | ----------- | ------| ------- | |
|
| mlabonne/NeuralMarcoro14-7B | 71.42 | 87.59 | 64.84| 65.64 | 70.74 | 72.046 | |
|
| udkai/Turdus | 73.38 | 88.56 | 64.52| 67.11 | 67.7 | **72,254** | |
|
|
|
Yes, as strange as it may sound, one can indeed increase ARC from 71.42% to 73.38 % with one single epoch of cca 1200 repetitive winograd schematas... |
|
|
|
# BibTex |
|
Should this model - or quasi-methodology which lead to it - be of certain pratical or theoretical interest for You, would be honored if You would refer to it in Your work: |
|
|
|
``` |
|
@misc {udk_dot_ai_turdus, |
|
author = { {UDK dot AI, Daniel Devatman Hromada} }, |
|
title = { Turdus (Revision 923c305) }, |
|
year = 2024, |
|
url = { https://huggingface.co/udkai/Turdus }, |
|
doi = { 10.57967/hf/1611 }, |
|
publisher = { Hugging Face } |
|
} |
|
``` |
