Downloads · 30 days
7
26% of all-time downloads
SFT-dk-qa-Llama-3.1-8B-Instruct-bc
ProjectZLLM/SFT-dk-qa-Llama-3.1-8B-Instruct-bc
SFT-dk-qa-Llama-3.1-8B-Instruct-bc is a machine learning model from ProjectZLLM. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
SFT-dk-qa-Llama-3.1-8B-Instruct-bc is a merge of the following models using mergekit: TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16merged TifTifR/SFT-qa-Llama-3.1-8B-Instruct-20-r16-1merged
All-time downloads
27
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Aug 23, 2024
- Updated
- Aug 23, 2024
- SHA
- 2384cace
Model card
From the Hugging Face model README
SFT-dk-qa-Llama-3.1-8B-Instruct-bc
SFT-dk-qa-Llama-3.1-8B-Instruct-bc is a merge of the following models using mergekit:
- TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged
- TifTifR/SFT-qa-Llama-3.1-8B-Instruct-20-r16-1_merged
🧩 Configuration
models:
- model: TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged
parameters:
weight: 0.5
- model: TifTifR/SFT-qa-Llama-3.1-8B-Instruct-20-r16-1_merged
parameters:
weight: 0.5
merge_method: breadcrumbs
base_model: TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged
parameters:
density: 0.9
gamma: 0.01
dtype: float16
- Type
- llama
- License
- apache-2.0
- Created
- Aug 23, 2024
- Updated
- Aug 23, 2024