piano-medley-7b

chargoddard/piano-medley-7b

piano-medley-7b is a text generation model from chargoddard. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.

Another experiment in the line of loyal-piano-m7.

Downloads · 30 days

0% of all-time downloads

All-time downloads

36.3K

Public

Parameters

7.2B

14.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.5 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: cc-by-nc-4.0
Model type: mistral
Access: Public
Created: Dec 10, 2023
Updated: Jan 4, 2024
SHA: 9ed35e21

Try a prompt

Datasets

Model card

From the Hugging Face model README

Another experiment in the line of loyal-piano-m7.

Steps taken to produce this model:

Train loyal-piano-m7
cDPO with HuggingFaceH4/ultrafeedback_binarized to produce loyal-piano-m7-cdpo
Train another model with different sampling of the same source datasets as loyal-piano, let's call it servile-harpsichord
cDPO servile-harpsichord with allenai/ultrafeedback_binarized_cleaned, Intel/orca_dpo_pairs, and a helpfulness-only version of PKU-Alignment/PKU-SafeRLHF
TIES merge several checkpoints of servile-harpsichord-cdpo with loyal-piano-m7-cdpo

Local benchmarks show the result to be better than any of the individual components. Let's see if that holds up!

Trained using the Alpaca prompt format.

Configuration for final merge:

models:
  - model: chargoddard/loyal-piano-m7-cdpo
    parameters:
      density: 1.0
      weight: 1.0
  - model: /home/ubuntu/servile-harpsichord-cdpo/checkpoint-4186
    parameters:
      weight: 0.1
  - model: /home/ubuntu/servile-harpsichord-cdpo/checkpoint-5796
    parameters:
      weight: 0.2
  - model: /home/ubuntu/servile-harpsichord-cdpo/checkpoint-6118
    parameters:
      weight: 0.3
  - model: /home/ubuntu/servile-harpsichord-cdpo/final
    parameters:
      weight: 0.4
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16
parameters:
  density: 0.4
  normalize: true
  int8_mask: true

Task: Text Generation
Library: transformers
Type: mistral
License: cc-by-nc-4.0
Created: Dec 10, 2023
Updated: Jan 4, 2024