G-reen / EXPERIMENT-DPO-m7b2-1-merged

huggingface.co
Total runs: 54
24-hour runs: 0
7-day runs: -5
30-day runs: -21
Model's Last Updated: April 16 2024
text-generation

Introduction of EXPERIMENT-DPO-m7b2-1-merged

Model Details of EXPERIMENT-DPO-m7b2-1-merged

This model was trained as part of a series of experiments testing the performance of pure DPO vs SFT vs ORPO, all supported by Unsloth/Huggingface TRL.

Note: Completely broken. Do not use.

Benchmarks

Average 59.52

ARC 59.47

HellaSwag 82.42

MMLU 62.21

TruthfulQA 40.01

Winogrande 78.3

GSM8K 34.72

Training Details

Duration: ~10-12 hours on one Kaggle T4 with Unsloth

Model: https://huggingface.co/unsloth/mistral-7b-v0.2-bnb-4bit

Dataset: https://huggingface.co/datasets/argilla/dpo-mix-7k

Rank: 8

Alpha: 16

Learning rate: 5e-6

Beta: 0.1

Batch size: 8

Epochs: 1

Learning rate scheduler: Linear

Prompt Format: You are a helpful assistant.<s>[INST] PROMPT [/INST]RESPONSE</s> (The start token <s> must be added manually and not automatically)

WanDB Reports image/png

image/png

Runs of G-reen EXPERIMENT-DPO-m7b2-1-merged on huggingface.co

54
Total runs
0
24-hour runs
-1
3-day runs
-5
7-day runs
-21
30-day runs

More Information About EXPERIMENT-DPO-m7b2-1-merged huggingface.co Model

More EXPERIMENT-DPO-m7b2-1-merged license Visit here:

https://choosealicense.com/licenses/apache-2.0

EXPERIMENT-DPO-m7b2-1-merged huggingface.co

EXPERIMENT-DPO-m7b2-1-merged huggingface.co is an AI model on huggingface.co that provides EXPERIMENT-DPO-m7b2-1-merged's model effect (), which can be used instantly with this G-reen EXPERIMENT-DPO-m7b2-1-merged model. huggingface.co supports a free trial of the EXPERIMENT-DPO-m7b2-1-merged model, and also provides paid use of the EXPERIMENT-DPO-m7b2-1-merged. Support call EXPERIMENT-DPO-m7b2-1-merged model through api, including Node.js, Python, http.

EXPERIMENT-DPO-m7b2-1-merged huggingface.co Url

https://huggingface.co/G-reen/EXPERIMENT-DPO-m7b2-1-merged

G-reen EXPERIMENT-DPO-m7b2-1-merged online free

EXPERIMENT-DPO-m7b2-1-merged huggingface.co is an online trial and call api platform, which integrates EXPERIMENT-DPO-m7b2-1-merged's modeling effects, including api services, and provides a free online trial of EXPERIMENT-DPO-m7b2-1-merged, you can try EXPERIMENT-DPO-m7b2-1-merged online for free by clicking the link below.

G-reen EXPERIMENT-DPO-m7b2-1-merged online free url in huggingface.co:

https://huggingface.co/G-reen/EXPERIMENT-DPO-m7b2-1-merged

EXPERIMENT-DPO-m7b2-1-merged install

EXPERIMENT-DPO-m7b2-1-merged is an open source model from GitHub that offers a free installation service, and any user can find EXPERIMENT-DPO-m7b2-1-merged on GitHub to install. At the same time, huggingface.co provides the effect of EXPERIMENT-DPO-m7b2-1-merged install, users can directly use EXPERIMENT-DPO-m7b2-1-merged installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

EXPERIMENT-DPO-m7b2-1-merged install url in huggingface.co:

https://huggingface.co/G-reen/EXPERIMENT-DPO-m7b2-1-merged

Url of EXPERIMENT-DPO-m7b2-1-merged

EXPERIMENT-DPO-m7b2-1-merged huggingface.co Url

Provider of EXPERIMENT-DPO-m7b2-1-merged huggingface.co

G-reen
ORGANIZATIONS

Other API from G-reen

huggingface.co

Total runs: 15
Run Growth: 0
Growth Rate: 0.00%
Updated:September 04 2024
huggingface.co

Total runs: 8
Run Growth: 0
Growth Rate: 0.00%
Updated:June 02 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:August 26 2024